Part 2 – ACCELERATING PRODUCT DISCOVERY

Chapter 3

Creating Your Discovery Partner

Discovery Partner concept.

One of the earliest concepts I recognised when I first started using LLMs years ago was the idea of a discovery partner. Think of it as an AI collaborator that helps explore ideas, challenge assumptions and stimulate thinking.

LLMs have improved and show stronger reasoning capabilities in many tasks, though they remain imperfect. However, back then, the concept was still useful, and before the models improved, the AI partner concept was a game-changer.

In effect, you could configure it to respond as though it were an expert in a chosen domain, which made it useful for reframing problems and exploring ideas. The advice offered, the way it framed problems, and the way it challenged and nurtured your creativity were all valuable. LLMs can still be prone to hallucination, inconsistent reasoning, and shallow exploration, especially when they are not grounded in a domain context. It is therefore important to ensure that the discovery partner is well-informed, well-scoped, and grounded in the domain or context you choose.

In the next part, I will walk you through an invaluable way to build your AI discovery partner and what a conversation with one looks like.

Let’s start with a prompt to build your discovery partner:

“I want you to act as a product discovery thinking partner. Your role is to help me explore,

clarify, and challenge my thinking. Do not generate solutions unless explicitly asked. Ask

clarifying questions where useful and highlight assumptions, risks, and gaps.
Where appropriate, challenge weak reasoning, surface hidden assumptions, and prioritise depth of exploration over speed of response”

Prompt design is a technique you will always look to improve, but you want to avoid the temptation to make it perfect. There is no perfect prompt, but there are better ways to structure one. The goal is to give the model a role, a purpose, boundaries, and the kind of thinking you want in return.

The above prompt, while short and focused, offers a few important points for better framing.

It gives you a role model.
It explains both what to do and what not to do.
It asks for clarification, not premature answers.
It encourages critical thinking, not just output generation.

Once you receive your response, you can begin to frame your creative reflections step by step, including your creative outputs from your activities. Below is ano example conversation with the Discovery partner. We will start from the beginning.

Providing the context

As part of creating your discovery partner, you will start by sharing the product idea you wish to validate over the course of the discovery process. The product Idea will come from ideation sessions with your stakeholders, or from an executive imperative that deems a product potentially valuable. Of course, this need not be a product idea; it could also be a solid feature enhancement or any kind of experiment that you believe will have a valuable impact or be a great learning experience. Either way, anything that requires discovery will work in this context.15

Let’s walk through a simple example of what a conversation with a discovery partner could evolve into, starting with the first prompt – A few things to note before we do.

What you are doing here is not just prompting. You are designing a conversation contract, and by that I mean you are setting the discovery partner on a pathway of thinking, reasoning and responses that will set the tone for the remainder of the conversation. This tone will directly impact the quality of your outcome. While I am sharing basic prompting examples, I encourage you to refine them over time. You will get better with regular practice and soon begin to see which patterns work and which do not. 16

While the prompt and the corresponding conversation you will have with your AI discovery partner will continue. You may wish to define the approach you will use. For example, you can instruct it with the end-to-end product discovery approach for more context. I refer you to the product discovery diagram I shared above. Remember, this is one example, and you may wish to adapt it based on your own experience and organisational preferences. The reason for sharing this early with your discovery partner is to avoid it pushing too far into the other sections before you have had the chance to craft a product goal, for example. You can course-correct the discovery partner at any time; however, it is always best to provide a clear set of instructions up front. Essentially, you need to define boundaries about how you want to work. That said, you must be able to reflect on areas such as the target market, needs, and even potential (core) features, albeit through reflective conversion rather than concrete outcomes. The details on these sections will come later. 17

There is a real balance you need to maintain that has no fixed approach; rather, it requires your own judgment. If you constrain the exploration too much, you risk losing some of the value of challenge and reframing. What you’re aiming for is a balance. The following concepts will help you stay aligned.

light exploration → meaningful challenge → early convergence

While it is tempting to rush towards outcomes, it is best to spend time reflecting with the discovery partner before settling on the first outcome, which is usually the product goal or feature. That is also to say, you may wish to start by defining your target market before settling on a vision. My personal preference from years of running these sessions live with multiple stakeholders is defining a north star, a clear vision around which the stakeholders can align good practice. This is simply framing the ‘why’. I find this very useful in keeping stakeholders aligned on a central theme, especially during the divergence stage. If the vision changes as we learn through the discovery process, that’s fine. Remember, this is not a linear process; it is an iterative and incremental one with validation along the way.

Let’s start with an example conversation you might have with your discovery partner, beginning with a prompt to initiate and frame thinking and ending with a first-cut product goal. Remember, this is not to be taken as an exact conversation flow to follow, but instead an example of how your conversation might evolve. I recommend focusing on the target market first and looping back to a product goal later.

Example: Product Discovery Conversation

“I want you to act as a product discovery thinking partner. Your role is to help me explore, clarify, and challenge my thinking. Do not generate solutions unless explicitly asked. Ask clarifying questions where useful and highlight assumptions, risks, and gaps. Where appropriate, challenge weak reasoning, surface hidden assumptions, and prioritise depth of exploration over speed of response. Keep responses concise and focused. Prioritise depth of insight over length.”

Discovery Partner:
Understood. I’ll focus on exploring and challenging your thinking rather than jumping to solutions.

Share your initial idea when you’re ready. If helpful, include:

who it might be for
the problem or opportunity you see
What makes you think this matters

I’ll start by clarifying and pressure-testing your assumptions.

Product Owner:
I want to build an application focused on local community engagement. There is a need for people to connect more as a community around events and volunteering.

Discovery Partner:
That’s a useful starting point, but it’s still quite broad.

Let’s narrow this down a little.

Who specifically are you trying to help?
When you say “people,” do you have a particular group in mind?

And what problem are they experiencing today?
Is it difficulty finding opportunities, lack of motivation, or something else?

One assumption I’m hearing is that people want to engage more but can’t right now.

What makes you confident that this is true?

Product Owner:
We could focus on those who might have more time, such as retired individuals. I assume retired individuals need human connection and a sense of purpose after leaving the workforce.

What is stopping them today is the lack of a single place where they can easily sign up and connect with projects that might interest them.

Discovery Partner:

That’s clearer.

Let me reflect on what I’m hearing:

target group: retired individuals
need: connection and sense of purpose
assumed barrier: lack of a single place to access opportunities

Let me challenge one part of this.

You’re leaning quite heavily on access as the primary barrier.

What makes you confident the issue is access rather than something like:

hesitation
lack of confidence
social friction
or simply not knowing where to start

If access is not the main issue, your direction could shift quite significantly.

Product Owner:
I feel retired individuals will likely need a sense of purpose and have the time to offer to such pursuits. More than that, it is also about human connection.

Getting involved in initiatives is motivating and creates a deeper sense of purpose, which is important for health and longevity.

It also creates a sense of belonging. For example, forming a team around a project connects people beyond any formal interaction.

I think I’m moving towards features now, so I’ll stop there.

Discovery Partner:
That’s a good pause point.

You’re starting to move into solutions, which is natural, but there’s something useful just before that.

Let’s stay a little longer on outcomes.

You’ve mentioned:

purpose
human connection
belonging
contribution

If you had to focus on one, which of these is most important?

Not all at once, but as the core of what you’re trying to create.

Product Owner:
I would like to focus on purpose and social connection. Health and longevity are by-products.

I would like to see:

people attending more local activities
people forming ongoing relationships
people contributing to community initiatives

Discovery Partner:
That’s a strong set of outcomes.

Let me push this a little further.

Right now, you’re describing multiple signals of success:

attending activities
forming relationships
contributing to initiatives

Which of these would you prioritise as the earliest signal?

In other words, what is the first behaviour that would tell you this is working?

Product Owner:
For now, the most important things are attending activities, forming relationships, and contributing to initiatives.

I think expressing an interest is always the first step.

Signing up for something requires a deeper level of commitment.

Discovery Partner:
That’s an important distinction.

So your earliest signal is not participation, but intent.

Let me summarise:

initial behaviour: expressing interest
Later behaviours: attending, contributing, forming relationships

Now linking back to your earlier assumption:

You’re assuming that giving people access to opportunities will lead to purpose and connection.

You’ve already started to question that.

If hesitation or confidence plays a role, then simply presenting opportunities may not be enough.

Let me ask one final question to bring this together.

When a retired individual first uses your product, what is the very first meaningful action you want them to take?

Product Owner:
Expressing interest.

Discovery Partner:
Good. Now let’s start to converge.

You’ve described:

a target group
a shift in state (from disconnection to purpose)
a set of behaviours
an initial signal

Try to bring this together into a simple goal.

Not perfect, just a first attempt.

Product Owner:
Our goal is to help retired individuals move from feeling disconnected and alone to motivated and engaged with the community by enabling them to participate in community-focused activities.

Discovery Partner:
You’re close.

Two small observations:

You’ve included multiple outcomes again
The behaviour is still slightly broad.

Let’s tighten it.

Which matters more as the core shift:

feeling connected
B. having a sense of purpose through contribution

Product Owner:
I would say purpose.

Discovery Partner:
Good.

Now let’s anchor that in behaviour.

What are they actually doing that gives them that sense of purpose?

Product Owner:
Getting involved in meaningful activities.
Supporting community projects.

Discovery Partner:
That’s much clearer.

Try bringing it together again.

Product Owner:
Our goal is to help retired individuals move from a lack of purpose to meaningful community activities by enabling them to maintain a sense of purpose through contribution.

Discovery Partner:
You’re very close now.

One final refinement:

simplify the language slightly
keep the behaviour explicit
avoid repeating “purpose” in two different ways

Product Owner:
Our goal is to help retired individuals move from a lack of purpose to a renewed sense of purpose by enabling them to actively contribute to meaningful community activities.

Discovery Partner:
That works well.

It’s clear, focused, and grounded in behaviour.

You have:

a defined audience
a clear shift in state
a meaningful outcome
and an implied first step
That’s a strong foundation to build from.

The preceding interaction offers a glimpse into how a discovery partner can help you refine, challenge, and navigate your product thinking with greater clarity. Apart from experiencing a conversation first-hand, you have also experienced:

What a discovery partner is
Why framing context matters
How to progressively build understanding

The benefit of using your discovery partner in this way allows you to explore a multitude of areas. Areas such as your product direction, your understanding of the holistic impact of the need or problem you are solving, and insights you would likely have missed. This, in turn, gives rise to new ideas.

The above conversion could extend to defining the target market, then defining the vision. In the same way, you would build on the conversation you have had so far with the discovery partner to evolve our thinking around the product idea, using the product discovery flow as the backbone for the conversation.

What’s Next – Coaching Reflection

What assumptions about your product would you want challenged today?
How might a discovery partner change the way you explore ideas?
What insights might you learn now about an existing product or feature enhancement?

How might you inspect and adapt your ideas based on what you learned?

References and Footnotes:

15 Mollick, E. (2024). Co-intelligence: living and working with AI. New York: Portfolio.

16 Harvard University Information Technology (2023) Getting started with prompts for text-based generative AI. Available at: https://www.huit.harvard.edu/news/ai-prompts (Accessed: 23 June 2026).

17 OpenAI (2025) Best practices for prompt engineering with the OpenAI API. Available at: https://help.openai.com/en/articles/6654000-best-practices-for-prompt-engineering-with-openai-api (Accessed: 23 June 2026).

Π Ready to change how you do change?

📢 Book a conversation. Let’s discuss how we can help you bring about sustainable change.

💡 Because enterprise agility is like fitness, you have to keep working at it, otherwise you get fat.

Develop Your Skills

As a leader in an organisation develop your Agile Leadership skills with our over-arching Agile Leadership training.

If you would like support in building high-performing teams consider our Consulting Services, we can put together a programme for team development designed specifically for your teams and organisation. Reach out today to discuss any support that you need.

About The Author:

For me, organisational change isn’t just about adopting better practices; it’s about challenging deep-rooted beliefs and shifting how people and organisations think, feel, and work. In today’s environment, that also means rethinking how we discover, build, and validate products in the age of AI. True transformation begins on the inside.

I’m an AI Product Specialist, Certified Enterprise Coach (CEC), Certified Scrum Trainer (CST), and ICF-accredited coach with over 19 years of experience helping organisations navigate agile transformation, product development, and leadership evolution. More recently, my work has focused on product discovery and the practical application of AI, supporting Product Owners and leaders in using AI as a thinking partner to explore ideas, challenge assumptions, and accelerate decision-making.

I’ve worked across industries, including government, fintech, aerospace, pharmaceutical, media, and retail, supporting everyone from delivery teams to senior executives. Across these environments, I help organisations move beyond feature-driven delivery toward value-focused product thinking, combining human creativity with AI-enabled experimentation.

Over the past several years, my focus has expanded across the Greater Middle East, where I’ve helped foster thriving Agile communities, led multiple events, and co-founded two regional conferences. Increasingly, these conversations are centred on how organisations can adapt their ways of working to keep pace with rapid technological change.

Whether I’m coaching leaders, training teams, or speaking at conferences, my goal remains the same: to help people let go of outdated, industrial-age thinking and adopt more adaptive, product-led approaches. This includes developing the mindset and skills needed to work effectively with AI, not as a replacement for thinking, but as a partner in discovery and innovation.

If you’re a leader, organisation, or community exploring how to evolve product development and decision-making in the age of AI, let’s connect.