You are on page 1of 60

Exclusively

with a PeopleCert
subscription

PRINCE2 7 ®

AI Practice
Guide
Global Best Practice
For everyone aiming to enhance their
AI skills in project management!

Official Practice Guide


PRINCE2 7 ®

AI Practice
Guide
Global Best Practice
For everyone aiming to enhance their
AI skills in project management!
Unlocking your
potential to
achieve more
Welcome to the PRINCE2® 7 AI Practice Guide.
Established in 2000, PeopleCert is the global leader in the certification industry.
PeopleCert develops global best practice frameworks and certifications, manages
exams, and delivers certifications. Its product portfolio in IT & Digital Transformation,
Project Management, Business, and Languages includes two of the most globally
recognized IP-protected frameworks, developed and evolved by the UK Government
over 30 years: ITIL® and PRINCE2®.
PeopleCert certifications are delivered across 200 countries and territories, 50.000
Corporates (82% of Fortune 500), and 800 government organizations through
a global network of 2.500 Accredited Training Organizations and 30.000 venues
worldwide, as well as through PeopleCert’s award-winning Online Proctoring
solution. PeopleCert consists of over 1.000 employees from 40 nationalities and has
received over 50 awards in Entrepreneurship, Business, Technology, and
Sustainability.

Powering
Best
Practice
Published by PeopleCert International Ltd.
Published in Cyprus
Publication printed in Greece or reproduced electronically in Greece

Copyright © 2023 PeopleCert International Ltd.

All rights reserved. No part of this publication may be reproduced or transmitted in any form and by any means (electronic, photocopying, recording or otherwise)
except as permitted in writing by PeopleCert International Ltd. Enquiries for permission to reproduce, transmit or use for any purpose this material should be directed
to the publisher.

Disclaimer
This publication is designed to provide helpful information to the reader. Although every care has been taken by PeopleCert International Ltd in the preparation of this
publication, no representation or warranty (express or implied) is given by PeopleCert International Ltd as publisher with respect as to the completeness, accuracy,
reliability, suitability or availability of the information contained within it and neither shall PeopleCert International Ltd be responsible or liable for any loss or damage
whatsoever (indicatively but not limited to, special, indirect, consequential) arising or resulting of virtue of information, instructions or advice contained within this
publication.

First edition PeopleCert International copyright 2023 (v 1.2 – Sept. 23)

ii PRINCE2® 7 AI Practice Guide | Global Best Practice | Copyright© PeopleCert International Ltd.
Contents
Chapters

1. About this guide 2


1.1 Welcome 3
1.2 A
 bout the authors 3
1.3 Format of the guide 4
1.4 P
 RINCE2 7 summary 4
1.5 Example scenarios 6
1.6 H
 ow to use the guide 10
2. General information 12
2.1 Purpose 13
2.2 T
 erms and concepts 13
2.3 Scope 14
2.4 S
 uccess factors 14
3. An introduction to AI in project management 18
3.1 Overview 19
3.2 T
 he AI spectrum 21
3.3 How PRINCE2 is AI ready 24
4. PRINCE2 7 and AI 26
4.1 Overview 27
4.2 P
 RINCE2 principles 27
4.3 People 30
4.4 PRINCE2 practices 32
4.5 PRINCE2 processes 37
4.6 The project context 39
5. Making it happen 48
5.1 Overview 49
5.2 T
 he digital and data management approach 49
5.3 Considerations 50
6. Recommendations for practice success 52
6.1 Recommendations 53
6.2 Be ready for exponential change: where next? 54

PRINCE2® 7 AI Practice Guide | Global Best Practice | Copyright© PeopleCert International Ltd. iii
Information icons and visual aids

Key message

Definition

Scenario 1: Data Knowledge

Scenario 2: Louistown City Council

Scenario 3: Findef

Scenario 4: NowByou

Management Product

iv PRINCE2® 7 AI Practice Guide | Global Best Practice | Copyright© PeopleCert International Ltd.
Chapter 1
About this guide
About this guide
Discover exclusive content

Chapter 1
with a PeopleCert subscription

1.1 Welcome
Welcome to the first PRINCE2 7 AI Practice Guide. In the fast-evolving landscape of artificial
intelligence, change is constant. This first iteration serves as an essential guide for understanding AI
in project management, but rest assured, it will not be the last. Harnessing the power of AI
alongside the PRINCE2 method can be a game-changer, unlocking unprecedented efficiencies and
capabilities in project delivery. Stay tuned for frequent updates that will keep you at the forefront of
global best practice in this exciting and ever-changing field.

1.2 A
 bout the authors
Andy Murray
Andy is the Executive Director of the Major Projects Association, prior to which he spent 30 years
as a practitioner, consultant, and assurer of complex projects and programmes for public, private,
and third sector organizations both domestically and internationally. He has a focus on project
governance, the treatment of inherent project complexity, and organizational development of
project capability.
Andy is a respected author, having worked with HM Treasury, Cabinet Office, the Association for
Project Management (APM), and PeopleCert to develop best practice guidance on their behalf.
Publications include PRINCE2, P3M3, Routemap, and the Governance of Co-Owned Projects. He is
the Chair of the APM’s Governance Special Interest Group and is leading on the Project Data
Analytics Task Force.
Andy is a collaborative and inclusive senior leader with a track record of building high-performing
teams both within his organization, across partnerships, and with voluntary groups.

Martin Paver
Martin is the Founder and CEO of Projecting Success, a leading authority on data-driven project
delivery, working closely with professional bodies, government departments, and industry to
transform how projects are delivered. Martin has successfully managed multibillion-dollar projects,
programmes, and portfolios, across industries in the private and public sectors. He regularly
advises governments and the private sector on their transition to data driven project delivery.
A recognized thought leader, he was the Co-Chair of the Project Data Analytics Task Force and was
named among the most influential people in data by DataIQ100 in 2021 and 2022. Martin founded
the 10,000+ member Project Data Analytics Community and Project:Hack, and is a member of APM’s
Data Advisory Group.
Martin is a Fellow of the APM, with a range of qualifications in PRINCE2, Agile, Lean MSP, portfolio
management, and holds an MBA in project management.

PRINCE2® 7 AI Practice Guide | Global Best Practice | Copyright© PeopleCert International Ltd. 3
About this guide
Chapter 1

1.3 F
 ormat of the guide
Welcome to the PRINCE2® 7 AI Practice Guide. This guide has been developed to help those working
on projects understand how AI can support them with a range of project tasks. It is the perfect
companion to the new AI-ready PRINCE2 7, the latest update to the world-renowned project
management method.

It is split into the following six chapters:


1. About this guide
2. General information
3. Introduction to AI in project management
4. PRINCE2 7 and AI in practice
5. Making it happen
6. Recommendations for practice success

1.4 PRINCE2 7 summary


PRINCE2, the world’s leading project management method, has evolved to meet the needs of the
future. It has been updated to reflect the modern realities of managing successful projects in the
21st century, incorporating the latest processes, tools, and technologies to stay ahead of the curve.
Best practice has now become even better!
PRINCE2 7 addresses changes in project management and adapts to evolving working practices and
technologies.
There are five integrated elements of PRINCE2 7 which are useful to be reminded of as you engage
with this guide:

Project
context

Practices People Processes

Principles

Figure 1.1 The five integrated elements of PRINCE2 (Official Book)

4 PRINCE2® 7 AI Practice Guide | Global Best Practice | Copyright© PeopleCert International Ltd.
About this guide
Chapter 1

PRINCE2 principles: the seven principles are the guiding obligations and good practices which
determine whether the project is genuinely being managed using PRINCE2. Unless these
following principles are applied, it is not a PRINCE2 project:


1. ensure continued business justification
2. learn from experience
3. define roles, responsibilities, and relationships
4. manage by stages
5. manage by exception
6. focus on products
7. tailor to suit the project.

People: an understanding of the needs, capabilities, and motivations of the people involved
and the relationships between them is crucial to how the project is established and managed.
People are at the centre of the PRINCE2 method.

PRINCE2 practices: these seven practices describe essential aspects of project management
that must be applied consistently throughout the project lifecycle:

1. business case
2. organizing
3. plans
4. quality
5. risk
6. issues
7. progress.

PRINCE2 processes: these seven processes in PRINCE2 provide the set of activities required
to direct, manage, and deliver a project successfully:

1. starting up a project
2. directing a project
3. initiating a project
4. controlling a stage
5. managing product delivery
6. managing a stage boundary
7. closing a project.

The project context: PRINCE2 has been designed so it can work within any context, including
in organizational and commercial contexts, delivery method, sustainability requirements, and
project scale. The principles, practices, and processes are applied by the people involved to
ensure that the method is fit for the project context.

PRINCE2® 7 AI Practice Guide | Global Best Practice | Copyright© PeopleCert International Ltd. 5
About this guide
Chapter 1

1.5 Example Scenarios


There are four example scenarios used throughout this guide, which demonstrate how AI can be
applied to a wide range of projects using the PRINCE2 method. A short summary of each scenario is
provided below. The icons on the left of the scenario boxes represent each of the scenarios when
they appear throughout the AI Practice Guide.

Scenario 1: Data Knowledge


Data Knowledge is a company with the mission of leveraging the power of big data
through advanced data analytics solutions. By analysing the wants, needs, desires, and
frustrations of social media users, Data Knowledge can transform raw and unstructured
data into reliable predictions that enable organizations to utilize consumer behaviours and
insights. However, they have not been as effective in using data to their own advantage
now that the company has over 300 staff. In fact, the head of the data science division
raised concerns in the last senior leadership team meeting.
The concerns were regarding the lack of visibility of who is working on what projects, poor
capacity planning, and claims of an overworked team with low morale due to the constant
juggling of commitments and firefighting issues. As a way of addressing this, the data
science division has been authorized to start a project to develop a time-recording
solution and a set of reports on project and task assignments along with resource
utilization and capacity planning. The reports are expected to offer interactive and
real-time insights that can enable data-driven decisions around the utilization and
planning of resources.
Data Knowledge has a defined framework for the management of projects. This is
expected to be a simple business change project, taking no more than three months in
the current financial year to complete.
Since Data Knowledge has in-house data analysis and app development capabilities as
well as clear requirements for this project, the project will be led by the head of data
science. They will work with the development division in an iterative and incremental
approach. This is to ensure that the solution can be deployed quickly to several new
projects and enhanced during its roll-out to the rest of the business.

6 PRINCE2® 7 AI Practice Guide | Global Best Practice | Copyright© PeopleCert International Ltd.
About this guide
Chapter 1
Scenario 2: Louistown City Council
Louistown is a historical town which is home to over 40,000 residents and attracts over
20,000 visitors per year. The city council has been criticized for the lack of investment and
modernization of the town centre. They have recently decided to improve the vibrancy of
the area and offer increased opportunities for business by approving the funds for the
‘Louistown is Open for Business’ (LOB) portfolio.
This is an ambitious portfolio of projects covering the next five-year plan cycle. A new
shopping centre, provisionally named ‘LouisShopping’, is seen as a key project within this
portfolio. This is a complex infrastructure project due to:
• the location of the building and historical nature of the surrounding buildings
• the requirement for the design to be consistent with the environment while offering
modern facilities supported by the latest technology
• the need to include underground parking space
• the importance of minimizing disruption to residents and businesses during the
construction works
• the recent award of ‘green town’ status to Louistown, and the sustainability
requirements this will impose on the development.
Due to the nature of the work, in which just the construction element is likely to span over
two financial years, the council has approved the strategic business case, the initial
high-level project plan and has appointed BuildyBrick as the main contractor. They have
established a requirement for a traditional delivery method in line with their standard
approach to projects.
The general view is that this project is long overdue, and the council would like
‘LouisShopping’ to be open to the public by the end of financial year three.

PRINCE2® 7 AI Practice Guide | Global Best Practice | Copyright© PeopleCert International Ltd. 7
About this guide
Chapter 1

Scenario 3: Findef
Findef was formed eight years ago with the promise to revolutionize how businesses
identify fraudsters, to protect the reputation of businesses, and to minimize financial risks.
The company experienced substantial growth in the first few years, transforming from a
niche small-medium-enterprise (SME) to one of the leading fintech firms in the field of
financial fraud, working with the world’s largest banks and merchants.
In the last 18 months, Findef’s growth has stagnated. This, coupled with the arrival of new
competitors, is creating discomfort among some investors. In response, the leadership
board recently approved the development of a suite of three innovative cybersecurity
products that will transform the market in financial risk management. Additionally, the
leadership board agreed that Findef will change its commercial and operating models to
exploit the new products to their full potential. The company will now deal directly with
the end user rather than through banks and merchants.
The FindefTwo programme has been established to oversee both the business
transformation and the development of the new products. As the programme requires
fresh investment, the board has established an investment committee that funds and
oversees the programme.
The project for the product development will use a hybrid approach of linear-sequential
for the overarching design and deployment of the product set and iterative-incremental
for the development of each product. The project also includes upskilling Findef’s DevOps
team in a new development platform.
To mitigate some risks, the project includes procuring advisors and a marketing agency
that could validate assumptions and share their product experience with the company.

8 PRINCE2® 7 AI Practice Guide | Global Best Practice | Copyright© PeopleCert International Ltd.
About this guide
Chapter 1
Scenario 4: NowByou
NowByou is a not-for-profit organization that works with local communities to eliminate
discrimination of any kind and help advance the international human rights system
through local and targeted interventions.
NowByou forms, chairs, and equips networking and support groups, where anyone who
has experienced discrimination can share their experiences and thoughts in a safe and
empowering space. Additionally, NowByou is one of the few non-governmental
organizations (NGOs) in the country that works directly with police forces to co-develop
campaigns that encourage the reporting of discriminatory incidents to authorities.
Recent research has shown that discrimination against marginalized groups, particularly
the homeless and refugees, is growing at a concerning rate. The increase in discrimination
has led NowByou to believe that a new six-month campaign is required to address this
issue. They have decided to run the campaign as a project, aiming to both raise awareness
of this type of discrimination and reinforce their own brand recognition (as NowByou is
highly dependent on the goodwill of donors and financial aid from partners).
The project management maturity of the organization is very low, with no standardized
processes or templates in place. For that reason, NowByou has contacted a professional
project manager with a track record of successful delivery in the not-for-profit sector who
will be responsible for:
• developing the initial project management documentation
• advising and coaching the NowByou director of campaigns, who is sponsoring the
project
• mentoring the staff member who will be appointed as project manager
• advise the project team how to use a variety of media (tv, press, and social networks)
for this, and other future projects.

PRINCE2® 7 AI Practice Guide | Global Best Practice | Copyright© PeopleCert International Ltd. 9
About this guide
Chapter 1

1.6 How to use the guide


Chapter 1 provides a quick reminder of the five integrated elements of PRINCE2 and introduces the
four scenarios that will be used to illustrate how AI can be applied on projects using PRINCE2.
Chapter 2 introduces key terms and concepts that will be used throughout this guide and highlights
factors for success.
Chapter 3 explains different types of AI from automation at one end of the spectrum to generative
AI at the other end. It also introduces key approaches such as prompting and discusses how
PRINCE2 is AI ready.
Chapter 4 then looks at each of the integrated elements of PRINCE2 to show, mostly by way of
example, how AI can be used to support them. It provides additional considerations on the
application of AI for each of the integrated elements.
Chapter 5 provides a deeper look at a new management product in PRINCE2, namely the digital and
data management approach, and explains how it can be used to consider and then establish the
use of AI on a project.
Chapter 6 recommends how AI can be successfully used on a PRINCE2 project. It considers the
pace of exponential change we are seeing in the development of AI and considers its future impact
on projects, project management, and the profession.

10 PRINCE2® 7 AI Practice Guide | Global Best Practice | Copyright© PeopleCert International Ltd.
Chapter 2
General information
Discover exclusive content
with a PeopleCert subscription

2.1 Purpose

General information
Chapter 2
Key message
Data analytics and the broader use of digital technologies and AI will transform how we
manage projects. PRINCE2 7 is ‘AI ready’, enabling its use through a requirement for a
digital and data management approach for the project. The digital and data
management approach is integrated in the method through the PRINCE2 practices and
processes.

The purpose of this guide is to provide practical guidance on how AI can be used to support project
management and specifically projects using PRINCE2.
Project management is the application of methods, tools, techniques, and competencies to enable the
project to meet its objectives. Project management involves the planning, delegating, monitoring, and
control of all aspects of the project and the motivation of those involved to achieve the project
objectives within expected performance targets.
Traditionally computers performed programmed tasks and their capability depended on the
directions in their programme. A change of context or requirement would typically require a change of
programme. AI now makes it possible for machines to learn from experience, adjust to new inputs,
and perform human-like tasks. Using deep learning and natural language processing technologies,
computers can be trained to accomplish a wider range of tasks. They learn by processing large
amounts of data and recognizing patterns in the data.
The purpose of using AI in project management is to help humans with project management tasks,
whether that is supporting decision-making through additional insights or automating routine
transactions. In both cases, AI is enabling humans to do things better; better decisions or more
efficient and effective transactions. Ultimately, the use of AI helps reduce or manage the uncertainty
and ambiguity typically associated with projects, which is the very purpose of project management.

2.2 Terms and concepts


AI is a broad term used to cover a wide range of digital technologies, data analytics, and machine
learning applications.
This guide uses the following terms to describe the AI spectrum:
Automation
The technology-enabled automation of business processes or routine tasks. Some automation is
performed by software robots, or ‘bots’, and is often referred to as robotic process automation or
RPA. RPA is often built into standard common IT platforms or apps, MS Office, or MS Excel.

PRINCE2® 7 AI Practice Guide | Global Best Practice | Copyright© PeopleCert International Ltd. 13
Data analytics
The systematic computational analysis of data or statistics. There are four types of data analytics:
• Descriptive, which answers the question, “what happened?” or “what is happening?”
• Diagnostic, which answers the question, “why did this happen?” or “why is it happening?”
• Prescriptive, which answers the question, “what should we do next?”
• Predictive, which answers the question, “what is likely to happen in the future?”
Generative AI
General information
Chapter 2

Generative AI involves the use of deep learning algorithms that can recognize, summarize, translate,
predict, and generate content (text, images, and other media) using very large datasets. They are
often referred to as Large Language Models (LLMs).
Digital technology
Digital technology is not part of the AI spectrum but is used in this guide to describe the use of
technology that complements the use of AI. For example, the use of augmented reality headsets to
assist with stakeholder engagement or design.
These terms and concepts are described more fully in Chapter 3.

2.3 Scope
The scope of using AI on projects is limitless, subject to ethical codes applied by the organization
commissioning the project and any governments or non-governmental bodies that have jurisdiction
over the organization.
The use of AI will fall into one of two categories:
• supporting project management, for instance planning
• supporting the delivery of the specialist work, for instance construction.
PRINCE2 is a universal method that can be applied to any type of project. Therefore, it does not
prescribe how to deliver specialist work. Similarly, the primary focus of this guide is how AI can be
applied to project management rather than specialist work, except by way of example using the
scenarios introduced in Chapter 1.
For projects that have development teams using agile development methods, the PRINCE2 team
manager role may be held collectively by the development team.

2.4 Success factors


The successful use of automation, data analytics, AI, and digital technology on projects include the
following three factors:

• One: ensure that the use of AI is considered from the outset through developing and maintaining
a digital and data management approach for the project.
• Two: understand the digital and data management capability your project needs through its
lifecycle, its current capability, and possible gaps. Have a plan to close the capability gap in time
for when you need it.

14 PRINCE2® 7 AI Practice Guide | Global Best Practice | Copyright© PeopleCert International Ltd.
• Three: check the digital and data management approach is consistent with the seven PRINCE2
principles.

2.4.1 Digital and data management approach


Success factor One: Ensure that the use of AI is considered from the outset through
developing and maintaining a digital and data management approach for the project.
The needs, opportunities, and approach for using AI on a project will vary by project. PRINCE2

General information
addresses this by recommending all projects to have a digital and data management approach

Chapter 2
specific to the project context. This management approach is developed early in the project
lifecycle, in outline during the process of starting a project and in detail during the process of
initiating a project. It will be reviewed and updated at every management stage. It enables a
proactive approach to including the use of AI on the project and ensures it is integrated with the
other management approaches, for example risk management.
See Chapter 5 for further guidance on the digital and data management approach.

2.4.2 Digital and data management capability


Success factor Two: Understand the digital and data management capability your project
needs through its lifecycle, its current capability, and possible gaps. Have a plan to close the
capability gap in time for when you need it.
The project does not exist in isolation of the organizations involved in the project, therefore
understanding digital and data management capability needs to be in the context of the
organization commissioning the project (the business) and those involved in the project ecosystem
(suppliers and users). There are numerous maturity models for assessing digital and data
management capability. These generally consider:
• Data governance: the process of managing the data lifecycle including how your organization
complies with relevant legislation and approaches ethical considerations relating to the use of
data.
• Data access: if you need large volumes of training data where will it come from? In-house,
bought-in, or via data pooling approaches such as a data trust?
• Data quality: how suitable is your data for its intended purpose?
• Digital and data security: how secure are your systems and data?
• Digital and data legacy: what will happen with your data when the project completes or when
systems become obsolete?
• Digital and data literacy and skills: the competency your team or organization in using AI on
projects.
• Data and digital leadership: how ambitious and committed is your leadership to embracing
new ways of working and removing barriers for practitioners.
• Systems and technology: how will the infrastructure required to support the use of AI on
projects be sourced? In-house, bought-in, or via a service?
The approach to deploying automation, data analytics, AI, and digital technology on projects will
vary depending on context. For example, the approach for an organization that uses projects for
business delivery, such as a supplier, will be different to an organization that mostly uses projects
for business change initiatives. Likewise, the approach for an organization that heavily uses data
analytics for business delivery, for example an insurance company, is likely to differ to those
organizations where data analytics is emerging across all its functions and operations as they will
already have a core capability and experience to draw upon.

PRINCE2® 7 AI Practice Guide | Global Best Practice | Copyright© PeopleCert International Ltd. 15
2.4.3 Alignment with the PRINCE2 principles
Success factor Three: Check the digital and data management approach is consistent with
the seven PRINCE2 principles.
The use of AI on a PRINCE2 project will be set out in its digital and data management approach. This
may include how diagnostic or predictive analytics are used to support decision-making at each
layer within the project (directing, managing, delivering). It may include automating some PRINCE2
processes or the techniques in the PRINCE2 practices. In some cases, it could even mean replacing
General information

some techniques with an AI-enabled alternative. Whatever the approach proposed, it should be
Chapter 2

checked for alignment with the PRINCE2 principles.


The seven PRINCE2 principles are:
• ensure continued business justification
• learn from experience
• define roles, responsibilities, and relationships
• manage by stages
• manage by exception
• focus on products
• tailor to suit the project.
If the use of AI is not consistent with any of these principles, then the project is no longer being
managed using PRINCE2.

16 PRINCE2® 7 AI Practice Guide | Global Best Practice | Copyright© PeopleCert International Ltd.
Chapter 3
An introduction to AI
in project management
Discover exclusive content
with a PeopleCert subscription

3.1 Overview
3.1.1 The pervasiveness of AI in work life
In the vast timeline of technological innovations, only a select few have transformed our lives,
societies, and economies as powerfully as the printing press, engines (steam, internal combustion,
jet), the Internet, and the advent of smartphones. Today, Artificial Intelligence (AI), and particularly
Large Language Models (LLMs) like ChatGPT, join this hall of fame of transformative technologies.
To truly comprehend the transformative nature of AI, consider this: the Internet brought global
information to our fingertips, and smartphones allowed us to carry that world in our pockets. AI,
particularly LLMs, takes this one step further by processing, understanding, and generating
information on our behalf. This is not just about accessing information, but also making it actionable,
personalized, and predictive.

in project management
An introduction to AI
AI in personal life

Chapter 3
AI is not confined to Silicon Valley labs or sci-fi movies anymore. Our daily lives are rife with its use:
• Cars: from Tesla’s self-driving capabilities to safety features like lane departure warnings or
fatigue detection, AI watches out for us on the road.
• Mobile phones: from predictive text to the use of Siri, Alexa, and Google Assistant, our AI
personal assistants, our mobile phones help us schedule, communicate, and entertain.
• Smart homes: from learning our preferred temperatures to optimizing our energy usage, smart
thermostats are perfect exemplifications of AI at home.
• Shopping: online platforms use AI to suggest products, optimize searches, and even detect
fraudulent activities.
• Health: wearable tech tracks our vital statistics, predicts potential health risks, and even suggests
dietary adjustments.
AI at work
The office is not immune to the AI revolution:
• Emails: AI-driven spam filters and priority sorting keep our inboxes manageable.
• Calendars: intelligent scheduling tools find the best meeting times considering the availabilities
of all participants.
• Documents and spreadsheets: tools like Grammarly or Excel’s forecasting functions utilize AI to
enhance productivity.
• Automation: repetitive tasks such as payment processing are now handed over to Robotic
Process Automation (RPA) systems.
• Chatbots: provide 24/7 customer service and assistance.
• Recruitment: AI-driven platforms screen applicants, match job requirements, and even schedule
interviews.
• Banking: fraud detection algorithms keep company finances secure.
Finding balance with AI
Humans excel in creativity, empathy, and contextual understanding, but some tasks are simply
cumbersome or challenging. That is where AI shines:

PRINCE2® 7 AI Practice Guide | Global Best Practice | Copyright© PeopleCert International Ltd. 19
• Information processing: AI can sift through vast data troves rapidly, something humans would
find time-consuming.
• Pattern recognition: detecting subtle patterns across large datasets is routine for AI, be it in
predicting weather or stock market movements.
• Avoiding cognitive bias: AI can be trained to make decisions free from human biases, leading to
fairer outcomes in areas like recruitment or loan approvals.
In essence, AI is steadily becoming our collaborative partner, amplifying our strengths, and
compensating for our limitations. As we stand at this tech crossroad, the path forward is one of
synergy between human potential and AI capabilities.
Let us not forget that the generation entering the workforce now has never known a world without
the iPhone. These ‘digital natives’ navigate tech-integrated lives seamlessly. For them, AI is not a novel
concept, but a foundational aspect of their digital experiences.

3.1.2 Applying AI on projects to support


successful outcomes
in project management
An introduction to AI

According to the Harvard Business Review, by 2027, approximately 88 million people worldwide are
expected to be working in project management, and the value of project-oriented economic activity
Chapter 3

will have reached $20 trillion1. Yet, the rate of successful project delivery in terms of effectiveness
and efficiency remains alarmingly low, at around 35%. This indicates an extravagant amount of time,
money, and opportunity is wasted1,2.

Analysis by Bent Flyvbjerg and Alexander Budzier from Oxford Global Projects3 on ~12,000 global
major projects concluded that the probability of a project being delivered on budget, on time, and
delivering the full benefits defined in the business case is only 0.5%2. That is only 1 in 200 projects
delivering on all their promises, so the scope to improve the initiation and delivery of projects is
huge, as is the scale of the economic impact.

How can project data analytics help improve project performance? If a project was a manufacturing
process it could have hundreds, if not thousands, of sensors generating performance data to
be analysed in near real-time with the ability to spot trends, model options, optimize controls,
and maximize yield. However, the typical project dashboard comprises around 10-20 data items,
reported a week or two after month end! Indeed, a RICS report claimed that 95% of project data is
not even used2.

A challenge is that project data is often siloed; sat in different organizations, or different functions
are in different departments within organizations. Projects are temporary, so data (beyond lessons
learned reports) is not always preserved after the project closes. This is partly why the world of
project management has been slow to embrace AI and data analytics in the same way as other
fields with shorter cycle times and more repetitive tasks, such as manufacturing.
This is changing, however. Project professionals are making the shift from projects being managed
as temporary initiatives operating outside of business-as-usual structures (resulting in slow and
manual collection and manipulation of data) to treating them as operational process which routinely
collects and uses performance data. The data is there, it is just that projects and organizations need
to establish the mechanisms and habits to collect and analyse more of it, more often, and from the
start.

1
https://hbr.org/2021/11/the-project-economy-has-arrived
2
https://majorprojects.org/blog/a-manifesto-for-data-driven-projects/#_ftn1
3
https://www.researchgate.net/publication/291945330_Why_Do_Projects_Fail

20 PRINCE2® 7 AI Practice Guide | Global Best Practice | Copyright© PeopleCert International Ltd.
Data analytics can help with project level decisions such as understanding changes in stakeholder
sentiment, assessing the productivity of individuals and teams, and understanding supply chain
risks. It can also help with portfolio level decisions, such as deciding which projects need the most
leadership support. Data analytics can do this by understanding which projects, or which tasks
within the project, are predisposed to variance or failure or how many projects are affected by
socio-economic or environmental trends or risks. Drawing parallels with the use of AI in personal
life, imagine having the project equivalent to the lane departure warning system in our cars:
constantly looking at your project, prompting you to take corrective action ahead of when it is
needed rather than after the next checkpoint or stage-end.
Pattern recognition capability in machine learning algorithms enable complex insights to be
uncovered which will improve decision making. This is possible if the algorithms have access to large
amounts of training data through data pooling. Project data permeates all aspects of project
management, so there are opportunities for project data analytics to cover the full spectrum of
project activities. The opportunities are endless. ef

3.2 The AI spectrum

in project management
An introduction to AI
Chapter 3
AI is loosely used to describe a spectrum of computer aided data processing, decision support, and
autonomous decision-making. In this guide we cover this spectrum in four groups, shown in Figure
3.1 The AI Spectrum

AI Spectrum

Generative
Automation Data Analytics & Visualization
AI/LLMs

Digital Technology
(e.g. sensors, augmented reality, virtual reality)

Figure 3.1 The AI Spectrum

Although generative AI receives a significant amount of media attention, it is only one part of the AI
spectrum applicable to the project management toolset. For many organizations and project teams,
their immediate opportunities may come from productivity improvements using automation,
improved decision making from insights gained using data analytics or the application of digital
technology specific to their project work, for instance the use of drones as part of quality assurance.
We explore the AI spectrum in the following four sections.

PRINCE2® 7 AI Practice Guide | Global Best Practice | Copyright© PeopleCert International Ltd. 21
3.2.1 Automation
Automation provides us with the capability to remove some of the manual, repetitive work. The
range of capabilities are vast, spanning a simple Excel macro through to a complex bot that mimics
human actions by interacting with applications and systems, performing tasks like data entry, data
extraction, and data manipulation, thereby increasing efficiency, and reducing human intervention.

Over the last 5 years robotic process automation has become commonplace. Operating as a
standalone toolset or integrated into the Microsoft technology stack via capabilities such as Power
Automate. These tools provide low code, drag-and-drop solutions to automate repetitive tasks,
integrate data and processes across different applications, and streamline business processes
without the need for extensive coding or development expertise.

These capabilities can be nested, enabling workflows to interact with each other and cross validate.
When set up effectively they can help to drive up data quality, consistency, and reliability.

There is a vast array of free resources available too, via tools such as Python, which can help with
data processing, including removing duplicates, handling missing values, and transforming data
into a standardized format. Python’s libraries like BeautifulSoup and Scrapy enable the extraction
in project management

of data from websites, allowing users to gather data from various online sources automatically.
An introduction to AI

Other Python libraries can help with schedule data-related tasks to run at specific intervals, such as
Chapter 3

periodic data updates or data validation. Project organizations will evolve from monthly reporting
to near real time data updates on demand. This can also include the automation of invoices, bill
payments, validation of work done, and much more. The opportunities are vast.

3.2.2 Data analytics & visualization


Project professionals often associate data analytics with reporting, typically via the increasing
use of dashboards and similar visualizations. Take the example of a car. The dashboard presents
the driver with the information relevant to the task. When data exceeds defined parameters, the
driver receives a warning indicator. The service interval is dynamic, based on how fast the car is
being driven. The same will apply to project dashboards. New entrants often unleash thousands
of visualizations that are uncontrolled and fall into disrepute. The more mature organizations bring
governance, role-based insights, with supporting data ecosystems. But visualizations are only one
aspect of data analytics.

Data analytics is the process of examining, interpreting, and transforming raw data into meaningful
insights and actionable information. It involves using statistical, mathematical, and computational
techniques to discover patterns, trends, and correlations within the data.

Data analytics can be broken down into 4 types:


• Descriptive Analytics: descriptive analytics focuses on summarizing historical data to provide
insights into past events and trends, helping to understand what has happened and identify
patterns in the data. This is where the bulk of the traditional project analytics is performed,
via progress reports, cost reporting, and earned value. However, if we are reporting on what
happened, how can we make effective decisions on what is in the past? Are we driving the car
by looking through the rear-view mirror rather than the windscreen, combined with a head up
display and Google Maps?
• Diagnostic Analytics: diagnostic analytics goes beyond descriptive analytics by delving into the
reasons and causes behind past events, seeking to answer why specific outcomes occurred
based on historical data. If used effectively it can be used to automate claims and dispute
resolution, continual learning, and providing feedback to future phases.
• Predictive Analytics: predictive analytics uses statistical and machine learning techniques to
forecast future outcomes and trends based on historical data, enabling organizations to make

22 PRINCE2® 7 AI Practice Guide | Global Best Practice | Copyright© PeopleCert International Ltd.
informed decisions and plan for potential scenarios. This could range from simple regression
through to more complex methods.
• Prescriptive Analytics: prescriptive analytics takes predictive analysis further by suggesting
optimal actions and strategies to achieve desired outcomes, helping businesses make data-
driven decisions by recommending the best course of action. Using these methods, we
acknowledge that the future is not predetermined, and our intervention can have a significant
impact on the outcomes.
Typically, 80% of a data scientist’s role involves collecting, preparing, and cleaning data rather
than the more appealing task of interpreting and extracting insights from data. Depending on the
nature of your project, the reality may be very different, particularly if your project involves lengthy
supply chains. The larger scale, more advanced projects will use common data environments and
integrated data pipelines, but this can be difficult to achieve when organizations already have their
existing tools and infrastructure. There is no one-size-fits-all solution.

3.2.3 Generative AI/LLMs


AI is a broad field aiming to create machines and systems that can perform tasks that typically

in project management
require human intelligence. These tasks can include learning, reasoning, problem-solving,

An introduction to AI
perception, speech recognition, and decision-making, among others. AI aims to create machines

Chapter 3
that can mimic human cognitive abilities and make autonomous decisions based on data and
algorithms. But when do machines become intelligent?

In 1950, the Turing Test, named after the prominent computer scientist Alan Turing, became the
theoretical method to assess the intelligence of an AI system. In this “imitation game,” as Turing
originally proposed, a human participant interacts with both a human and a computer without
knowing their identities. If the computer can convincingly deceive the human participant into
believing it is also human, then it is considered to have passed Turing’s test. Recent developments in
LLMs have delivered performance that exceeds that of a human, for specific use cases.

Machine learning is a subset of AI that enables machines to learn from data without being explicitly
programmed for a particular task. In machine learning, algorithms are used to analyse and learn
patterns from data, and the machine uses these patterns to make predictions, classify new data, or
make decisions. It relies on the availability of data and its quality to improve performance over time
through continuous learning and refinement.

Generative AI is a branch of AI that focuses on creating and generating new data, often in the form
of images, text, audio, or other multimedia content, based on patterns and knowledge learned from
existing data. Unlike traditional AI models that are designed for specific tasks, generative AI models
can produce original content and can be used for tasks such as image synthesis, text generation,
music composition, and more.

In a project delivery context, a good example is generative design in construction. A capability


that leverages computational algorithms and artificial intelligence to automatically generate and
explore multiple design alternatives for a given project definition. It involves defining a set of design
constraints and objectives, such as material properties, budget, safety standards, and then using
algorithms to iteratively create and evaluate numerous design options. The goal is to find the
most efficient, structurally sound, and optimized design that meets the specified criteria, allowing
architects and engineers to explore creative and innovative solutions that might not have been
discovered through traditional manual design processes. These capabilities were initially based on
logic or rules, but more recently they are exploiting generative AI.

If we can already design bridges and motorways using generative design, how long will it be until we
can generate options that balance and optimize for schedule, return on investment, carbon, safety,
cost, and a variety of other factors? The technology exists, but the profession lacks the integrated

PRINCE2® 7 AI Practice Guide | Global Best Practice | Copyright© PeopleCert International Ltd. 23
data and models to underpin it; but this is changing.

Large Language Models (LLMs) are a type of generative AI. LLM is trained on vast datasets, often
containing billions of words, to recognize patterns, grammar rules, and semantic relationships
between words and sentences. This training enables it to predict the most likely next word in
a sentence, generate coherent paragraphs, and understand the context of words in different
circumstances. These capabilities can be enhanced further when combined with other AI methods,
such as Midjourney or Stable Diffusion that use a LLM to understand the text prompt and then
diffusion models to gradually subtract noise and yield a picture that resembles images from its
source data. Users assist in continually improving the quality of the outputs.

Within a project context, LLMs can be trained as chatbots to answer questions around a corpus
of documentation. This could range from PRINCE 2 documentation and templates through to HR
policies, accounting, and tax. By training the LLM on project data, the chatbot will be able to answer
questions relevant to that dataset, such as comparisons between different reporting periods,
outliers, trends, and much more.

Capabilities such as Microsoft Copilot will take these capabilities further by extracting the
results and automatically visualizing them within a dashboard in PowerBI. These capabilities will
fundamentally change how project professionals extract, integrate, validate, interrogate, and
in project management
An introduction to AI

visualize data.
Chapter 3

3.2.4 Digital technology


The use of digital technology will vary by project use case. Construction projects will increasingly use
cameras, IOT sensors, wearables, and much more to provide real time insights into performance
on the project. Capabilities such as MAFIC help to measure productivity of each member of the
workforce and use this to inform different shift patterns, training, or other interventions. A company
called Buildots uses helmet mounted cameras to collect imagery on site, integrate with the 3D
model, and measure progress against plan, rescheduling in near-real time. The more successful
organizations will be those who can integrate this data end-to-end, including across their supply
chain to optimize, successfully navigate constraints, and respond to real time challenges.

Transformation projects will make greater use of sensemaking capabilities. Gauging where the
project is delivering results and where interventions are needed. This could include capabilities
such as the MeetingQuality add-on to web conference platforms that provides insights into team
cohesion, surfaces lead indicators of misalignment, and much more.

Augmented reality will help to blend the real and virtual worlds. Assisting everything from
walkthroughs, on-demand documentation, methods, and much more.

3.3 How PRINCE2 is AI ready


PRINCE2 has been designed to be universal and flexible. That means it can be applied to any type of
project, in any type of organization. It also means it can be applied and tailored to be supported by
any type of tool, whether an off-the-shelf project management tool, an in-house tool, or a collection
of tools both off-the-shelf and in-house. The use of tools to support the directing, managing, and
delivery of the project is captured in each of the management approaches, for example the risk

24 PRINCE2® 7 AI Practice Guide | Global Best Practice | Copyright© PeopleCert International Ltd.
management approach, and is then considered in a coherent way in the digital and data
management approach.
Each management product in PRINCE2, such as a plan, describes the management information
expected but not how it is obtained, generated, or presented. The emphasis is on how the
information is used to support decision-making. This is reflected in the PRINCE2 processes, with
each process activity showing the information from which management products is to be used as
an input, should be checked, or reviewed, or will be generated as an output.
The digital and data management approach establishes how the project will get, use, and maintain
data to enable good decisions that will initiate and deliver the project in a controlled way. This can
include any use of technology across the AI spectrum introduced in this chapter.
Remember, PRINCE2 describes what needs to be done, not how it is done; whether by hand, semi-
automated, automated, or AI assisted.

in project management
An introduction to AI
Chapter 3

PRINCE2® 7 AI Practice Guide | Global Best Practice | Copyright© PeopleCert International Ltd. 25
Chapter 4
PRINCE2 7 and AI
Discover exclusive content
with a PeopleCert subscription

4.1 Overview
This chapter looks at each of the five integrated elements of PRINCE2 to show, mostly by way of
example, how AI can be used to support them. It provides further considerations on the application
of AI for each of the integrated elements, comprising of:
• PRINCE2 principles
• people
• PRINCE2 practices
• PRINCE2 processes
• the project context.
The scenario examples and the considerations for each of the five integrated elements of PRINCE2
in this chapter help readers to explore how the spectrum of AI (described in chapter 3) can be used
on their project.

4.2 PRINCE2 principles


The PRINCE2 principles are the guiding obligations that determine whether the project is genuinely
being managed using PRINCE2. They ensure effective application and tailoring of PRINCE2 to any
project.

PRINCE2 7 and AI
Chapter 4
The seven PRINCE2 principles are:
• ensure continued business justification
• learn from experience
• define roles, responsibilities, and relationships
• manage by stages
• manage by exception
• focus on products
• tailor to suit the project.

PRINCE2® 7 AI Practice Guide | Global Best Practice | Copyright© PeopleCert International Ltd. 27
4.2.1 Overview of where AI can help
The table below shows where AI can best help which PRINCE2 principle.

PRINCE2 principles

Automation Data Analytics & Visualization Generative Digital


AI/LLMs Technology
Manage by stages Ensure continued business justification Learn from AI
experience
Manage by Define roles, responsibilities, and
exception relationships Tailor to suit
the project
Focus on products

For decades, the project profession has been capturing lessons learned. Project practitioners
capture lessons in their lessons log and then reflect on those to document in a lesson learned
report of what went well and how to improve. The challenge has always been how to take the
lessons in those reports and turn them into action. In 2009 PRINCE2 introduced the principle of
learning from experience with a ‘pull’ rather than ‘push’ philosophy. That is, it is the duty of everyone
working on a project to seek lessons from other similar tasks, work packages or projects and apply
them to their work.
If we now imagine this principle in the context of a Google Map or Waze. We can use AI to help us
navigate a route through our project, to optimize and help us with key decisions at specific points.
The amount of data being generated and captured by people, projects, and organizations is growing
at an exponential rate. Making sense of huge volumes of data is a challenge for humans, which is
where advanced data analytics and AI can help. The evidence-based insights gained can help inform
the development of the PRINCE2 method and make best practice even better. The codification of
PRINCE2 7 and AI

project management insights into global best practice enables a generic approach to be provided.
Chapter 4

AI will enable us to turbocharge these assets to be ‘tailored to suit the project’, which could range
from suggesting a logic flow or duration for a scheduled work package through to scenario-based
recommendations on courses of action. Lessons learned is no longer about the abstracted insights;
we can leverage the entirety of our experiences.
We can ingest large volumes of data into LLMs to gain applicable insights. For example, we can ask
the model what the key challenges are likely to be on our next work package. We can use advanced
data analytics to drill into the data to understand probabilities, which mitigations have previously
been most successful, and recommend appropriate tolerances. But the user needs enough
experience to understand when the answer is logical and when the model is ‘hallucinating’, or
generating false information. There could be several versions of this model. One that uses public
data and provides the best answer based upon the data it has been trained on. Or an organization-
specific model that is trained on their own corpus of data, which increases relevance. Imagine that
OpenAI is a model that has been trained to speak English and the organization-specific model is
taught the local dialect.

28 PRINCE2® 7 AI Practice Guide | Global Best Practice | Copyright© PeopleCert International Ltd.
4.2.2 Scenarios

Scenario 2: Louistown City Council


The project manager at Louistown City Council is leading three different projects and is
overstretched. She is time poor. The PRINCE2 principle of managing by exception is
incredibly important to her, but she is notified of exceptions too late to positively influence
them. She decides to deploy advanced data analytics and AI to help her with the
assurance activities. The team use data analytics to understand the level of process
adherence, such as whether the team plans are being managed well, by deploying Python
scripts on project records. BuildyBricks has recently bought an AI planning tool which has
been trained on hundreds of thousands of construction projects to predict the schedule
and cost profile based on the breakdown of the work. They have set up automatic alerts
in their system if the schedule or cost is forecast to exceed tolerance thresholds defined
by the algorithms. These alerts are dynamic, adjusting to the stage in the project lifecycle.
The Council is also exploring how to integrate the planning data with other data, such as
technical queries or early warning notices, to improve the performance of the algorithms.

Scenario 4: NowByou
NowByou lacks the professional project delivery skills to deliver the project and their
charity donations have been reduced since COVID. They can no longer afford to recruit
external support for this role. They appointed Sue, their campaign manager, to manage
the project. She uses a LLM to guide her step by step through the process and draft the
project initiation documentation, which she refines specifically for her project. She also
asks the model for advice on the most suitable campaigns and measures of effectiveness.

PRINCE2 7 and AI
She learns about Google Analytics and similar KPIs, pulling data out via an API into

Chapter 4
PowerBI to create a real time dashboard on the effectiveness of the campaigns.

4.2.3 Considerations
The PRINCE2 principles underpin the method and are reflected in each of the integrated elements
of people, practices, processes, and project context. Therefore, it is more a case of how AI is applied
to the project whilst being consistent with the principles than it is of where AI helps each of the
principles.

PRINCE2® 7 AI Practice Guide | Global Best Practice | Copyright© PeopleCert International Ltd. 29
4.3 People
In PRINCE2, the ‘people’ element of the method covers those who are working on a project and the
relationships between them, as well as those impacted by a project.
The people element of the method includes guidance on:
• leading successful change
• leading successful teams
• communicating.
The success of a project will depend on how well the project establishes strong relationships with
the organizations that support its delivery, as well as how it fits into the organizational ecosystem to
deliver the change. Projects combine a unique set of people from across the business, user, and
supplier communities for a limited period. To successfully deliver the project, all levels of leadership
must establish a project culture that motivates people.

4.3.1 Overview of where AI can help


AI can help project teams understand the complexity of such relationships, automate the collection
and dissemination of information which aids communication and insights, or use augmented reality
or virtual reality to simulate the project product or the journey to deliver it (the project plan) to
engage stakeholders as part of the change management approach.
The table below highlights where AI can be applied to PRINCE2 people across the AI spectrum.

People

Automation Data Analytics & Visualization Generative Digital


PRINCE2 7 and AI

AI/LLMs Technology
Chapter 4

Consultation Consultation (understanding) Generating the Support for


(collation) draft hybrid working
Sentiment analysis of stakeholders
communications
On-boarding and across the project ecosystem and AR/VR
management
off-boarding organizational ecosystem simulation of
approach and
(engagement) project product
Responding to the change
or project plan
enquiries or FAQs Network analysis (of relationships management
(engagement)
through a project approach
chatbot
Generating
communications
content

30 PRINCE2® 7 AI Practice Guide | Global Best Practice | Copyright© PeopleCert International Ltd.
4.3.2 Scenarios

Scenario 4: NowByou
NowByou has planned an initial consultation to inform their main campaign. They wanted
to use generative AI and RPA to support the consultation work and explained their use in
their communications management approach. Their early market engagement identified
four personas they wanted to target. These ranged from an HR professional who has a
deep understanding of discrimination through to someone who is unconsciously
discriminating against others. They used ChatGPT to develop six scenarios and then set
up storytelling chatbots on their website with which consultees could interact to explore
different types of discrimination. They used a Microsoft form to capture feedback to
enable them to better target their messaging. They then used ChatGPT to refine and
hyper-personalize the messages for the different personas, taking account their level of
awareness and understanding, for the main campaign.

Scenario 1: Data Knowledge


Data Knowledge has a problem with its team being overworked, but it does not have the
volume of work in the pipeline that justifies the need to work long hours. Something is
going wrong somewhere. Emily, their project lead, works with the data science team to
extract activities and durations from diaries. She integrates this with the sprint plan and
deliverables. Two weeks later, she concludes that the team is spending over 25% of their
time in meetings. She then used an app to understand what value people were getting
from the meetings and found that attendance had grown over time, and many people
were only there because they were invited. Emily asked the meeting organizers to

PRINCE2 7 and AI
rationalize attendance to key decision makers. She also used AI to summarize the key

Chapter 4
outcomes from each meeting and circulate via Teams channels to keep everyone
appraised of progress. She reduced the 25% of time in meetings to 10%.

4.3.3 Considerations
When developing the digital and data management approach for the project, consider the following
in relation to people:
• Privacy of stakeholders in the project ecosystem and organizational ecosystem and whether
anonymisation, pseudonymisation, or similar approaches are required.
• Security of personal data and insights. Role based access will be required.
• Ethical use of insights gained.
• Whether there are any blind spots in insights or engagement due to some stakeholder groups
being less digitally connected than others.
• Understand the diversity of the training data used for LLMs when generating content as it
may inadvertently reduce diversity in its output. For example, some open access generative AI
platforms for artwork have been shown to create images of mostly white men for manager roles.
• Danger of using data to target specific groups or people.

PRINCE2® 7 AI Practice Guide | Global Best Practice | Copyright© PeopleCert International Ltd. 31
4.4 PRINCE2 practices
Practices are aspects of project management that must be applied consistently and throughout the
project lifecycle. The PRINCE2 practices require specific treatment of that aspect of project
management for the PRINCE2 processes to be effective.
The seven PRINCE2 practices are:
• business case
• organizing
• plans
• quality
• risk
• issues
• progress.
PRINCE2 practices describe aspects of project management that must be continually addressed as
the project progresses through its lifecycle. PRINCE2 provides guidance for effective management
and suggested techniques for each practice.

4.4.1 Overview of where AI can help


The PRINCE2 practices are designed to help the project management team apply and tailor the
method, principally through a suite of management approaches (such as the benefits management
approach). Each management approach defines the procedures, techniques, and standards to be
applied and the responsibilities for that aspect of project management to be effective. LLMs such as
OpenAI’s ChatGPT can generate the draft content for these management approaches based on
PRINCE2 7 and AI

information provided in the project brief. This is not the same as using a template as the drafts
Chapter 4

generated will be based on the project’s context. The better trained the LLM is, the better the draft of
the management approach will be.
This is why some organizations are using the open-source LLM platforms and training it on sector or
organizational data.
The table on the next page highlights where AI can help each of the PRINCE2 practices across the AI
spectrum.

32 PRINCE2® 7 AI Practice Guide | Global Best Practice | Copyright© PeopleCert International Ltd.
PRINCE2 practices

Automation Data Generative Digital


Analytics & AI/LLMs Technology
Visualization
Business case Diagnostic / Generate draft Data pipelines for
predictive business case benefit measures
(modelling of based on project (pre, during, post
options and brief project)
impacts)
Organizing Workflow of Blockchain
governance regarding
arrangements, for commercial
example approval arrangements
authority
Impact on roles
Plans Logic, sequencing, Generate draft BIM
resource plans based on
optimization project brief and
business case
Quality Assess quality of Generate draft AR/VR quality
outputs vs a product assurance
training data set descriptions
Risk Diagnostics Generate initial
(root-causes and risk register based
responses) on project brief
and business case
Predictive

PRINCE2 7 and AI
(modelling of Recommend

Chapter 4
‘what if’ scenarios) responses to risks
and contingency
Move towards
allocation
variance analytics
Issues Diagnostics Recommend
(root-causes and responses to
responses) issues
Progress Automated, Generate Interrogate Sensors for
real-time forecasts progress via assessing
reporting natural language progress
Generate
checkpoint
reports, highlight
reports, and end
stage reports
using dashboards

PRINCE2® 7 AI Practice Guide | Global Best Practice | Copyright© PeopleCert International Ltd. 33
4.4.2 Scenarios

Scenario: organizing practice


Findef has a complicated project team structure, with a significant amount of external
support. They have a well-defined RACI, but the decision-making process is regularly
impeded because of problems with interfaces between corporate systems that have been
set up for ‘business as usual’ rather than project work. Findef implemented a decision-
making workflow process based on the project RACI that assigns tasks to specific people,
which in turn trigger other actions when completed. The automation engine performs an
assurance check on each step of the workflow to check for compliance or quality issues,
ensuring that the next step has the best chance of success. The project manager has a
real-time dashboard that tracks the progress of key decisions. The decision-making
workflow system highlighted that Brian from the marketing agency is consistently late
approving designs due to being overloaded. The project manager uses this evidence to
renegotiate the level of support provided by the agency.

Scenario: business case practice


Data Knowledge has outline approval to begin the project, but Emily who would have
written the detailed business case is on sick leave. The data science team ingest 20 other
business cases into their localized LLM and asked it to draft a detailed business case for
this project based on the project brief. Within one hour, they have a draft which they
circulate to relevant stakeholders to refine. By the end of the day, they submit the detailed
business case to release the required resources. The approvals team use their own LLM
to identify potential challenges for this project, note that the majority of these have been
PRINCE2 7 and AI

identified, and authorize the team to proceed.


Chapter 4

Scenario: risk practice


The project manager at Data Knowledge intends to hold a risk workshop to help prepare
the risk management approach and the initial risk register. To help guide the workshop,
the project manager uses ChatGPT to explore likely risks and potential mitigations.

Prompt: We want to develop a time recording solution for our projects. What risks should we
prepare for given our context?
Response: Given the context provided, Data Knowledge is attempting to internalize its own expertise
by developing a time-recording solution to address concerns raised about resource management.
Here are some potential risks they might face:
• Unclear Requirements or Scope Creep: even with clear initial requirements, there might be
changes or expansions in the scope as the project progresses. This can extend the timeline and
increase the costs.
• Technical Challenges: implementing a real-time, interactive reporting system can introduce
technical difficulties, especially with data integrations and ensuring data accuracy.
• User Adoption: not every staff member might be enthusiastic about tracking their time or using
a new tool. Resistance can reduce the effectiveness of the system.

34 PRINCE2® 7 AI Practice Guide | Global Best Practice | Copyright© PeopleCert International Ltd.
• Data Privacy Concerns: time-recording can be seen as invasive or micromanaging. There might
be concerns about how the data is stored, accessed, and used.
• Resource Overallocation: with the data science division handling both their regular tasks and
this project, they might become overburdened, leading to potential delays or reduced quality in
both areas.
• Inadequate Testing: given the short timeframe of three months and an iterative approach, there
is a risk of inadequately testing the system, leading to potential bugs or inefficiencies when it is
rolled out.
• Dependency on Key Personnel: if the project is highly dependent on the head of data science
or a few key individuals, any absence or turnover can jeopardize the project timeline.
• Mismatch of Expectations: the leadership might have high expectations regarding the system’s
capabilities, and if not managed, there could be disappointments with the end product.
• Incomplete Integration: given that the solution is expected to provide insights on various
aspects (task assignments, resource utilization, etc.), there is a risk of some elements not being
integrated seamlessly.
• Underestimation of Project Complexity: as this is seen as a “simple business change project,”
there is a risk of underestimating its complexity, leading to unforeseen challenges.
Mitigation Strategies:
• Frequent Communication: regular check-ins with stakeholders to ensure everyone is aligned
with the project’s progress and any changes in scope.
• User Training: provide adequate training to staff members to ensure they understand and can
efficiently use the time-recording solution.
• Feedback Loops: given the iterative approach, gather feedback from early users and adjust
accordingly.
• Clear Data Policies: clearly outline and communicate how the data from the time-recording
solution will be used and ensure all measures are GDPR compliant (or compliant with relevant
data protection laws).
• Resource Backup: have a backup plan or additional resources available in case of unforeseen

PRINCE2 7 and AI
challenges or overburdened team members.

Chapter 4
• Thorough Testing: even in an iterative approach, ensure each iteration is rigorously tested
before deployment.
• Set Clear Expectations: manage expectations by clearly defining the project’s objectives, scope,
and limitations upfront.
The project manager is particularly concerned about the suggested risk of incomplete integration, so
sought further insight from ChatGPT on this area.
Prompt: How can Data Knowledge reduce the risk of incomplete integration if it uses an agile
approach to product development?
Response: Using an Agile approach to product development offers several strategies and practices
that can help Data Knowledge reduce the risk of incomplete integration. Here is how:
• Incremental Development: Agile promotes the development of small, incremental changes. By
building and integrating features piece by piece, you can ensure each part works correctly before
moving on to the next.
• Continuous Integration (CI): CI is the practice of frequently integrating code changes into a
central repository. After changes are integrated, automated tests are run to ensure the new code
integrates correctly with the existing system.
• Regular Demos and Feedback Loops: at the end of each sprint, the team showcases the
implemented features to stakeholders. This provides an opportunity to check if the integration
meets business needs and to gather feedback.
• Cross-functional Teams: Agile teams are often cross-functional, meaning they have members

PRINCE2® 7 AI Practice Guide | Global Best Practice | Copyright© PeopleCert International Ltd. 35
with different skills and expertise (for example developers, testers, business analysts). This helps
ensure that the integration aspect is considered from various perspectives.
• Automated Testing: Agile emphasizes automated testing, which can detect integration issues
early. By having a suite of regression tests, the team can be confident that new code has not
broken existing integrations.
• Definition of Done (DoD): the DoD is a clear and concise list of requirements that a software
increment must adhere to for the team to call it complete. Ensuring that “integration” is a part
of this definition will guarantee that features are not considered “done” until they are fully
integrated.
• Frequent Refactoring: Agile promotes regular refactoring to improve code quality. By
continuously improving the codebase, the team can ensure that integrations are kept clean and
efficient.
• Pair Programming: two developers working on the same piece of code can catch integration
issues earlier and can discuss and address potential integration challenges on the spot.
• Daily Stand-ups: these are short daily meetings where team members discuss what they worked
on the previous day, what they plan to work on today, and any blockers they might have. Any
integration issues or concerns can be quickly highlighted and addressed.
• Use of Integration Tools: tools like Jenkins, Travis CI, or CircleCI can help in automating the
integration process, running tests, and ensuring that all components work harmoniously.
The project manager delves into a few more of the suggested risks with follow-up questions. They
use the ChatGPT responses to add further project specific content to the project’s draft risk
management approach and initial risk register. The suggested risks are aligned to Data Knowledge’s
own risk categorization, based on the PESTLE technique as recommended in PRINCE2. The draft risk
management approach and risk register are reviewed and refined in the risk workshop. Ahead of the
risk workshop, the project manager consults with the manager of the DevOps team to find out if or
what integration tools the company is using.

4.4.3 Considerations
PRINCE2 7 and AI
Chapter 4

When developing the digital and data management approach for the project, consider the following
in relation to AI enabled PRINCE2 practices:
• Specialist help may be needed to establish workflows between organizations on different
corporate systems.
• How does the project (or organizations involved) get access to the volumes of training data
required, particularly for forecasting. Is this available in-house if the organization has a large
portfolio of projects? Or would the project or organization need to make use of data trust or
benchmarking service?
• Be aware of whether the project has siloed or connected data. The key insights come from the
connections in project data, for example linking schedule and cost data.
• How will the project ensure that it is compliant with legislation or business policies relating to
Personally Identifiable Information (PII) and commercially sensitive data?

36 PRINCE2® 7 AI Practice Guide | Global Best Practice | Copyright© PeopleCert International Ltd.
4.5 PRINCE2 processes
PRINCE2 is a process-based approach for project management. There are seven processes in
PRINCE2 that provide the set of activities required to direct, manage, and deliver a project
successfully.
The seven PRINCE2 processes are:
• starting a project
• directing a project
• initiating a project
• controlling a stage
• managing product delivery
• managing a stage boundary
• closing a project.

4.5.1 Overview of where AI can help


A process in PRINCE2 is a structured set of activities that define the sequence of actions and their
inputs and outputs to achieve a specific objective. Therefore, using automation to support
processes improves their repeatability, consistency, and efficiency.
The table below highlights where AI can help each of the PRINCE2 processes across the AI
spectrum.

PRINCE2 processes

PRINCE2 7 and AI
Automation Data Analytics & Visualization Generative Digital

Chapter 4
AI/LLMs Technology
Establish BI dashboards to show status, diagnose Embedding
workflow to process performance issues, and PRINCE2 into a
automate triggers prescribe improvements project
from one process management
to the next system.

PRINCE2® 7 AI Practice Guide | Global Best Practice | Copyright© PeopleCert International Ltd. 37
4.5.2 Scenarios

Scenario: controlling a stage process


Data Knowledge has a key challenge relating to capacity planning. They created a low code
time-recording application that allows employees to log their work hours, project
assignments, and tasks. In parallel, they created a list of resources, skills, and constraints.
They deployed the open-source PuLP algorithm in Python to solve optimization problems,
including resource allocation and capacity planning, using linear programming techniques.
This provided a first order analysis of how best to assign resources. They developed the
capability further by leveraging time sheet data to understand the relative productivity of
each member of the team and feed this parameter into the resource model. They can now
dynamically assign resources taking account of emerging priorities and constraints.

Scenario: starting a project process


Findef is an organization that is expert in understanding financial risks. A large component
of their in-house capability concerns the deployment of graph databases and AI to identify
patterns that flag the risk of fraud. They decided they wanted to use their pattern
recognition capability on prioritizing the product roadmap in the FindefTwo programme.
They wanted to map the projects, products, resources, constraints, and market feedback.
A multi-dimensional challenge, with an added time component. The team utilized internal
expertise to develop a graph database that mapped the interconnections between each
of these attributes, then added additional richness around key project variables for each
new product such as cost, variance, and more. They were able to query the database and
rapidly understand the composition of their product roadmap, which automatically fed
PRINCE2 7 and AI

into the programme plan and provides the trigger for the starting a project process for
Chapter 4

each new product to be developed. The trigger from their graph database and AI engine
provides a project mandate containing a draft project product description based on the
understanding of desired features and optimal market timing.

4.5.3 Considerations
When developing the digital and data management approach for the project, consider the following:
• As an organization aggregates and collates data it becomes a significant risk should it ever be
compromised. Always consider how to develop guardrails and data partitioning to mitigate this
risk.
• When deploying AI, consider how to make best use of patterns in the supporting data. A project
may be entirely unique when looking through a product lens, but there may be a lot of similarities
with other projects when viewing through a functional lens.

38 PRINCE2® 7 AI Practice Guide | Global Best Practice | Copyright© PeopleCert International Ltd.
4.6 The project context
The principles, practices, and processes in the PRINCE2 method are applied by the people involved
to ensure that the method is fit for the project context. PRINCE2 has been designed so it can work
within any context.
There are five common contexts included in the PRINCE2 Official Book to illustrate how the method
can be applied or tailored:
• organizational context, such as sector, capability, culture, policies
• commercial context, such as contracts, relationships
• delivery method, such as lifecycle model, development techniques
• sustainability requirements, such as business drivers and priorities
• project scale, such as complexity, duration.

4.6.1 Overview of where AI can help


PRINCE2 processes
Automation Data Generative Digital
Analytics & AI/LLMs Technology
Visualization
Organizational Development of In-house project
in-house LLM to management
include business system based on
policies, the use of

PRINCE2 7 and AI
standards, and PRINCE2

Chapter 4
methods management
products
Commercial Automation of Analysis of tender Drafting of Blockchain for
contract notices submissions procurement procurement,
(such as changes, documentation fulfilment,
early warning invoicing, and
notices, claims) payments

Automating
invoicing and
payments based
on work package
approval
Delivery method Data analytics of
(iterative- user feedback to
incremental inform next sprint
approach)
Continued on next page

PRINCE2® 7 AI Practice Guide | Global Best Practice | Copyright© PeopleCert International Ltd. 39
Continued

PRINCE2 processes
Automation Data Generative Digital
Analytics & AI/LLMs Technology
Visualization
Sustainability Use of sensors on
requirements project equip-
ment/plant to
minimize idling or
inefficient use
Project scale Small projects will
rely on off-the-
shelf or open-
source tools

Large projects
may have a
centralised
business provid-
ing data analytics
services to
projects
PRINCE2 7 and AI
Chapter 4

40 PRINCE2® 7 AI Practice Guide | Global Best Practice | Copyright© PeopleCert International Ltd.
4.6.2 Scenarios

Scenario 2: Louistown City Council


The government uses a risk potential assessment to characterize the complexity of a
project, which shapes the level of assurance and support required. Louistown City Council
wanted to deploy this methodology to assess how best to assure their portfolio of
projects. But they were concerned that the approach was not sufficiently dynamic to take
account of the emerging conditions such as high rates of inflation, poor availability of
some building materials, the eventuality of another pandemic. They developed a simple
app that automated the risk potential assessment, which identified specific areas of focus.
They also set up an automation script that regularly queried the credit rating and
Companies House data for key suppliers. They also linked this to public data from the
county’s Contracts Finder website to understand how much government work each
supplier had won. This provided a lead indicator of whether the contractor had too much
work on (which could adversely impact resources available to the project) or too little,
which could be an indicator of financial distress. Automatic triggers were set up to initiate
additional due diligence for stressed suppliers.
The Council wanted to secure best value for money for the taxpayer by ensuring they
used the right form of contract for each project and contractor. They realized that a
one-size-fits-all approach to contracting was not appropriate. They developed a simple
decision tree-based algorithm to select the best form of contract for each project. They
used automation to extract key parameters for each prospective contractor from emails,
company registration and trade association websites to populate the contract
boilerplates, before performing an automated assurance check prior to issue. The
automation process extracted the key parameters from each contract into a portfolio
management tool, recording details such as project start, finish, value, key milestones etc.
This was integrated into PowerBI and regularly reviewed by the CEO to understand overall

PRINCE2 7 and AI
Chapter 4
cashflow. The team used Python to extract invoice values from emails, enabling them to
report forecast against actuals. They deployed AI to learn from this data to provide a
dynamic forecasting capability, reflecting performance on the ground.
BuildyBricks is the prime contractor on the Louistown project. They have bought a
capability that uses AI and LIDAR that runs daily scans of each room on the construction
site. They take these images and integrate them with their 3D model. They can see where
actual progress has been made against the planned variance and flag any divergence. This
allows them to automatically replan the following day’s activities, plan logistics, and
optimize work phases. They use this data to forecast end dates and report, in near real
time, to the client. As a main contractor, BuildyBricks appreciate that the key to a long-
term successful relationship with the Council is to drive up productivity, reduce cost, and
improve delivery confidence. They are experts in Lean and the Theory of Constraints.
They have a long-term strategic plan to create a fully integrated model of their
construction sites that leverages real time data feeds. They have deployed a hard hat
capability that uses sensors to track head movement to understand personal productivity.
They run experiments to understand the impact of shift patterns and weather on
personal output. They move to a two-break shift pattern model and drive-up workface
productivity by 14%. They use machine learning to integrate pit lane deliveries with crane
availability and logistics to ensure optimized ‘flow’ across site. The key to all of this is their
level of ambition, vision, skills, and end-to-end data integration.

PRINCE2® 7 AI Practice Guide | Global Best Practice | Copyright© PeopleCert International Ltd. 41
4.6.3 Considerations
When developing the digital and data management approach for the project, consider the following
in relation to project context:
• Consider the vast range of data sources that may be available to you. Some are available via
third party data aggregators. Others are available directly and can be accessed via APIs or web
scraping tools such as BeautifulSoup.
• Do not just automate the existing process. Take a step back to reimagine the process end-to-end.
There may be a better way to deliver the outcomes.
• Build error checking and resilience into the process from the outset.
• Consider maintenance of the code too. Upgrades in libraries and code may stop the application
from working, requiring the code to be reconfigured.
PRINCE2 7 and AI
Chapter 4

42 PRINCE2® 7 AI Practice Guide | Global Best Practice | Copyright© PeopleCert International Ltd.
Chapter 5
Making it happen
Discover exclusive content
with a PeopleCert subscription

5.1 Overview
PRINCE2 7 is ‘AI ready’, enabling its use through the requirement for a digital and data management
approach for the project.
The digital and data management approach is developed in outline in the starting a project process,
completed in the initiating a project process and updated for each stage of the project through the
managing a stage boundary process. The digital and data management approach underpins
PRINCE2’s progress practice in terms of establishing a data-driven approach to understanding
current and forecast progress, but it is also used by each of the other six PRINCE2 practices. It is the
management product that brings it all together so that the project has a considered and coherent
approach to the use of AI and technology.

5.2 The digital and data


management approach
Purpose
The purpose of the digital and data management approach is to describe:
1. how digital technology will be used to support project management (for example project controls)
and project work (for example the use of digital twins for design and construction)
2. how data and information will be created, used, and managed across the project ecosystem and
through the project lifecycle and afterwards.

High-level content
Scope: describes what data is to be managed.
Digital technology requirements: an analysis of the digital technology the project will need by
considering the automation and facilitation of project management activities and any specialist
technology required to support the specialist project work. In some cases, this may involve the use
of systems already established by the business and suppliers. In other cases, different or additional
systems may be needed.
Data management requirements: an analysis of the data the project will generate or needs by
Making it happen
Chapter 5

considering:
• What data or information is needed or will be created?
• Where will the data come from?
• Where will the data be held?
• How will the data be kept secure?
• What level of privacy is required?
• How the data or information will be analysed, curated, and presented?
• Who will have access or rights? How integrity will be ensured?
• How will data quality be assured?
• What will happen to the data after the project is completed?

PRINCE2® 7 AI Practice Guide | Global Best Practice | Copyright© PeopleCert International Ltd. 45
Digital and data management procedures: description of any digital and data management
procedures to be used on the project (based on the analysis of the digital and data management
requirements).
Responsibilities: who will be responsible for the roles associated with the digital data management
approach.
Timing formal digital and data management activities: for example, the implementation of
systems, the timing of any data audits, or the provision of a data room to support procurement
activities.
Supporting tools or systems: describes what tools or systems will be used for digital and data
management.
Standards: describes any digital and data management standards required for the project.
References: for any associated documents or products.

5.3 Considerations
5.3.1 Data management
The product outline for the digital and data management approach includes some considerations
relating to data:
• What data or information is needed or will be created?
• Where will the data come from?
• Where will the data be held?
• How will the data be kept secure?
• What level of privacy is required?
• How the data or information will be analysed, curated, and presented?
• Who will have access or rights?
• How will integrity be ensured?
• How will data quality be assured?
• What will happen to the data after the project is completed?
These questions prompt the project management team to be proactive about how data will be used
Making it happen
Chapter 5

to support decision making and project controls. The project context will greatly influence the
approach. For example, most of the data to support the project in the Data Knowledge scenario will
exist within or will be generated by the organization itself. Whereas, in the Findef scenario, they will
need to source market and user data externally to help inform product design and development
decisions.
Once the project management team understands the data management requirements for the
project, they can then consider their options and develop the management approach. When
developing the management approach, they will need to factor the data management capability of
the project team and the organizations involved; this will comprise data literacy of key decision
makers such as members of the project board, data skills of the project manager and project
support, data access, and the provision of automation, data analytics or generative AI technology to
make use of the data.

46 PRINCE2® 7 AI Practice Guide | Global Best Practice | Copyright© PeopleCert International Ltd.
5.3.2 Digital technologies
Digital technologies can help with both project management and project delivery. Technology to
support project management will mostly be in support of the data management approach
described in 5.3.1. Technology to support project delivery will depend on the delivery method and
may be specific to each stage and each work package within the project. For example, the
technology to support the work packages involved in design or the technology to support the work
packages involved in construction.
There may be some crossover between technology to support project management and technology
to support project delivery. For example, the use of Augmented Reality (AR) headsets can be used in
design but can also provide data for managing requests for change or for capturing details for
issues and risks.
The project management team will need to consider how the technology across the project will be
sourced, set up, integrated, maintained, used, and decommissioned.

Making it happen
Chapter 5

PRINCE2® 7 AI Practice Guide | Global Best Practice | Copyright© PeopleCert International Ltd. 47
Chapter 6
Recommendations for
practice success
Discover exclusive content
with a PeopleCert subscription

6.1 Recommendations
The successful use of automation, data analytics, AI, and digital technology on projects requires
changes at the individual, project, and organizational levels. It may also change the profession of
project management.
The following five recommendations cover these different levels:

Recommendation Comments PRINCE2


element
Individual Competitive advantage will come for those who People
develop your data make better decisions based on insights gained from
literacy and skills AI. Knowing the provenance of your data, the type of
algorithms used, and the type of metrics used in the
outputs is now a core skill for project professionals.
“In a world of change, the learners shall inherit the
earth, while the learned shall find themselves
perfectly suited for a world that no longer exists. As
a leader, you must embrace change and remain a
student, or find yourself perfectly suited for a world
that no longer exists”. Eric Hoffer4
Project Be curious. How is AI being applied to other parts of All PRINCE2
make deliberate and your work and life and could that same approach practices
conscious decisions on work on your project?
how you use AI on your Where and how can your project benefit from
project increased use of automation, data-analytics, and AI
on your project?
Capture these decisions in the project’s digital and
data management approach.

Project/organization Automating poor practices or poor processes may Learn from


focus on data first, just make issues happen faster. Making decisions experience
then systems based on bad data is likely to result in bad decisions. principle
Therefore, the primary focus needs to be on data.
What data do you need, where will it come from, how
will you use it and keep it secure, what will happen to
it when the project completes.
Project/organization Organizational design and development should People
understand the digital/ cover capability gaps in the project. Organizing
data capability you have practice
and what you need?
Continued to the next page
Recommendations for
practice success

Chapter 6

4
https://www.goodreads.com/quotes/51399-in-a-world-of-change-the-learners-shall-inherit-the

PRINCE2® 7 AI Practice Guide | Global Best Practice | Copyright© PeopleCert International Ltd. 49
Continued

Recommendation Comments PRINCE2


element
Profession Projects are complex, involving lots of uncertainty All aspects
and ambiguity. Some elements of project
can data analytics and
management may be better understood through
AI solve persistent areas
deep learning algorithms than what we have gained
of under-performance
from research to date. Some elements of project
that methods and
management may be better performed by AI than
models have struggled
humans.
to address?
We all need to be ready for be ready for exponential
change (see below).

6.2 Be ready for exponential change:


where next?
We live in exponential times where the rate of change is accelerating. Following a launch in 1999, Netflix
took 3.5 years to achieve 1 million users. Spotify took 5 months from launch in 2008. ChatGPT took 5
days. Threads took 1 hour5.
Azeem Azhar remarked that “if the primary cause of the exponential gap is our failure to predict the
cadence of exponential change, the secondary cause is our consequent failure to adapt to it. As the
speed of change increases, our society remoulds itself at a much slower pace. Our institutions have an
in-built tendency towards incrementalism”6. In the last 30 years project delivery has changed very little.
Project data is typically a by-product of the project delivery process, an exhaust plume. As organizations
begin to recognize its strategic importance the volume of project data properly captured will grow
exponentially. They will recognize that there are sources of data that are being overlooked. Data that,
when integrated, helps enhance AI model performance. The data integration challenge will become
exponentially more difficult, requiring cross-organizational collaboration on a scale we have never
imagined. The climate emergency places additional pressure on all of us to work and think differently.
Commercial competitive advantage will become secondary to collegiate working, with major clients
rewarding those organizations that move the dial in the interests of society. Effective project delivery
holds the key to unlocking many of the solutions that will help us to get to net zero and improve climate
resilience.
We are in the middle of a perfect storm. How will you and your organization respond?
It may be helpful to reflect on four possible futures, and what this means for you and your organization:
1. Project professionals supported by data professionals: project professionals continue
along the current path and leverage a service from a separate data function to create data
pipelines, apps, and insights. The rate of progress will be constrained by the vision, bandwidth,
and appetite for transformational change, which will vary by organization. The more progressive
and visionary organizations will outperform their peers.
Recommendations for
practice success

Chapter 6

5
https://www.statista.com/chart/29174/time-to-one-million-users/
6
https://www.wired.co.uk/article/exponential-age-azeem-azhar

50 PRINCE2® 7 AI Practice Guide | Global Best Practice | Copyright© PeopleCert International Ltd.
2. Data professionals supported by project professionals: data professionals review every part
of the project delivery process and explore how to automate, integrate, and accelerate it. The
ultimate objective could be to create a fully automated project or get as close to it as possible.
Removing interfaces, automatic creation of schedules, automated creation and review of
documentation, designs, logistics optimization, and more. Even stakeholder engagement can be
hyper-personalized to an audience of one using LLM. There will always be a human in the loop,
but how close to full automation will they get?
3. A blended team: where project professionals acquire new skills, supported by a data centre of
excellence. Project professionals develop the knowledge to leverage tools to free up capacity.
This creates the bandwidth to engage with the data team to reimagine how projects are
delivered. They begin to run experiments and pilots at pace, feeding back and iterating. This can
be accelerated x100 by collaborating across organizational boundaries. Rather than pursuing a
headcount/cost reduction methodology, they pursue approaches that deliver a step change in
project delivery performance. Better insights, better decisions, better projects, better
outcomes.
4. The bots take over: the rate of progress is dictated by the vendors. New capabilities emerge
from OpenAI, Microsoft, Oracle, and others that challenge the fundamentals. They target the
very essence of project delivery, leveraging vast amounts of data that already exists within the
cloud. Imagine a capability such as Midjourney, where the images become better and better as
humans engage with it and help it to learn. The same could apply to project management.
Each of these futures is possible and probable.

6.2.1 Individual/personal perspective


The challenge for all of us is whether project data analytics will become a function of the IT and data
team, or an integral part of project delivery roles.
We see a range of responses. Some people who are curious but rely on others to find ways of
applying automation, data analytics and AI on their project (whether from within the project team or
from a central IT or data team). Other people who have acquired new skills who have been
promoted into new roles that simply did not exist a year ago. They are developing new products and
services for their organization, driving up delivery performance and unlocking new ways of working.
There are also people who are acquiring new skills, but their organization does not yet have the
infrastructure and systems in place to enable them to flourish.
Our advice is simple:
1. acknowledge that we are now in a new era
2. embrace the opportunities to free you and your colleagues from repetitive and
burdensome work
3. use this additional capacity to acquire new skills, immerse yourself in understanding the art
of the possible
4. evaluate whether you would like to become a practitioner or a translator; someone who
understands how the capabilities work, how they can be leveraged and forge a bridge
between data, IT, and project teams to enable change
5. pilot, be bold and experiment, use these experiments to understand your data, constraints,
obstacles and who the advocates are. If you do not have the support you need, consider a
move to somewhere that embraces data-driven project delivery.
What could this mean for project delivery roles? The future is unknown, but we offer some possible
developments.
Recommendations for

• Risk managers: we tend to view risk management as a process, underpinned by a range of


practice success

different systems, risk registers and tools. Ultimately, we are guessing what may go wrong,
Chapter 6

quantify this guess, integrate it within a schedule, apply Monte Carlo analysis then derive a very
precise three-point estimate that becomes encoded in future business cases. Imagine a future

PRINCE2® 7 AI Practice Guide | Global Best Practice | Copyright© PeopleCert International Ltd. 51
where we pivot towards variance analytics, where we recognize that variance can emerge from
risk, change control, technical queries, and a multitude of other sources. If we acquire a deeper
understanding of the extent to which events, work packages, or activities are predisposed to
variance, we can target our effort. As we increasingly understand causality, we can deploy probes
and identify early warnings to capture this variance earlier. We also use these methods to tailor
our approach to whether we are working within an ordered or complex adaptive system. It could
become a very different role.
• Stakeholder managers: we often think of stakeholder management in the context of power and
influence grids, which are often static documents. If we pivot our thinking around influencers,
we begin to target the small percentage of people who have the large impact on outcomes. We
can measure this in near-real time. We can use LLMs to tailor messaging to specific stakeholder
groups, then tailor again based upon any previous communication or their perceived level of
support. We see our role as influencers rather than trying to manage stakeholders. Many of them
simply cannot be managed, but we can get better at understanding them and trying to win them
over.
• Benefits managers: this will no longer be a process-centred around benefits mapping. Those
who are proficient in data will be adept at understanding the decision trade space, modelling
scenarios, and informing decisions at key points. Benefits will become more extensive, linked to
the UN Sustainable Development Goals and beyond. Benefits managers will understand how
decisions impact these goals or enhance return on investment in the broadest sense. Those
who can leverage insights from their peers will ultimately deliver better performing models,
augmenting human intuition. They will be data driven, rather than process driven.
• Project managers: there is an opportunity to pivot the approach away from process centric
outputs to real time insights, fed by a steady stream of validated and integrated data. The project
managers who can see around corners, identify emerging issues much earlier, and leverage the
hard-won experience from other projects will outperform those who do not. They unlock new
superpowers which would otherwise not exist. They will also have the data to challenge intrinsic
bias, encouraging key stakeholders to reflect on their position or decisions.
This does not just require people just to learn how to use new tools or wrangle data, but to unleash
the art of the possible.

6.2.2 Organizational perspective


The organizational perspective is inextricably linked to ambition. To what extent does the
organization want to move the dial on how it delivers projects? Is project data analytics a bolt on
established ways of working or an integral part of reimagining project delivery.
The approach will also change based upon organization type. Will advanced data analytics provide
your organization with a competitive advantage? Will you use the data to develop new tools that
provide part of your SAAS offering? Will those who hoard the most data ultimately have better
trained models? Or are you a public client that seeks to extract more value from each dollar of
investment by leveraging the hard-won experience of all those projects that have gone before,
encouraging competition based on innovation rather than data hoarding or narrow commercial
interests? These perspectives will often be in conflict, requiring clients to establish new ways of
working and reward those who are collegiate, building on the shoulders of those who have gone
before.
Another perspective is organizational design. Is data an enabling service or an integrated part of
everything that your organization does? How will it be used to reimagine project delivery and drive a
step change in performance? This will drive the organizational design. From the level of investment
through to governance, data integration, data access, new methods and tools, real time insights, and
Recommendations for

much more. It depends whether you are a tier 2 contractor within a broader ecosystem or a
practice success

Chapter 6

dominant tier 1 contractor who can dictate the rules.

52 PRINCE2® 7 AI Practice Guide | Global Best Practice | Copyright© PeopleCert International Ltd.
6.2.3 P
 roject management profession
perspective
Project data analytics will challenge the very essence of a body of knowledge. A compendium of
good practice that has evolved over the years. As data volumes grow, we will be able to provide
evidence to demonstrate which practices and methods work best in which situations. The insights
will become dynamic and adapt to context. We can train LLMs on not only the methods and
processes, but all the variance events, design queries, trade-off decisions, norms, and much more.
We move beyond an instruction manual to a fully integrated project assistant.
LLMs need large volumes of data to be trained on. A challenge for the project management
profession is how we access the data to train them as project data tends to be siloed or not
maintained due to the temporary nature of projects. We see several scenarios:
1. The big tech firms such as Google, Microsoft, and Amazon develop project management
solutions based on the data they harvest.
2. Tool vendors use your data through permissions you agree to in the licence agreement.
They train their tools with the data they have (including yours) and then charge their clients
for the insights gained through further subscriptions or use the insights for competitive
advantage to gain new clients and retain existing ones.
3. Companies establish their own LLMs based on their own project data. Likely to be viable
only for larger organizations with large volumes of projects.
4. Data trusts are set up for industry sectors, possibly by industry or trade associations, where
they pool their data across multiple organizations with specific arrangements for how data
is cleaned, anonymised, secured, and accessed. There are several data trusts in existence to
date, for example the Construction Data Trust in the UK.
5. National governments establish data lakes from the data generated from publicly funded
projects through legislation, and then make the insights or data available to different
degrees depending on the organization requesting access to it. This is already happening to
some extent, but there are limitations on how far into the supply chain the governments
can get the data from.
6. Professional bodies and other IP owners develop their bodies of knowledge using data from
a combination of the above.
What underpins all these future possibilities is challenge and opportunity. The opportunity for
professionals to reskill and upskill and for organizations to gain competitive advantage by leveraging
technology alongside proven best practice to improve project success. As the world around us
evolves, we too must adapt, innovate, and stay at the forefront.

PRINCE2® 7 AI Practice Guide | Global Best Practice | Copyright© PeopleCert International Ltd. 53
Your opinion matters!
Please take a few minutes to give us your feedback about the PRINCE2® 7 AI Practice Guide
by completing our online Feedback Form here.

PeopleCert is accredited by Lloyd’s (UK) in accordance


with ISO 14001 for Environmental Management, since
ESG 2006. Recognized through numerous awards, we
Commitment remain committed to ESG leadership and the
preservation of our planet.

You might also like