April 9, 2026
This is the third blog in Mike’s 8-part series about how AI can become a force for clarity and acceleration across the broader software development lifecycle.
While the advent of AI-powered software delivery is accelerating coding for engineers, it’s also exacerbated a key challenge for Product Managers: the shortage of time they have for inherently human endeavours like discovery, collaboration, and strategic thinking.
In a series of eight blogs, enterprise software veteran and Product & Strategy Principal at Equal Experts Mike Mitchell shares his beliefs on how we can not only reset this balance between cross-functional delivery teams, but also give Product Managers even more time than they had before.
To explore our approach of a shared context across discovery and specification, our team used Claude Code, drawing inspiration from Teresa Torres’ recent work with the tool. Claude’s strength in both writing and coding makes it well suited to product teams operating across discovery and delivery.
A file-based structure was implemented to support transparency and portability between LLM ecosystems. Rather than introducing a separate product tooling layer, discovery artefacts were stored directly alongside engineering assets in the existing code repository in GitHub. This ensured that product and engineering operated from the same environment and reduced handoff friction.
Artefacts were primarily markdown files, organised into three categories:
With minor adjustments, this structure can be adapted for other AI tools such as OpenAI Codex. The key architectural decision is not the tool itself, but the shared source of truth: product and engineering work from the same repository, source files, and context.
Because LLM performance still degrades as tokens are added to the context window of each conversation, the architecture deliberately keeps inputs lean and targeted, providing an index for the model to find what it needs rather than loading everything at once.
With shared context established at the file and repository level, the next step was to define how discovery and delivery activities would evolve throughout the delivery lifecycle.
Read the full Evolving product discovery for AI delivery eBook
Mike Mitchell is a Product and Strategy Principal at Equal Experts, helping organisations adopt modern product practices and integrate AI into their product lifecycle in practical, sustainable ways.
His current focus is on helping product teams do more meaningful strategic work with AI, both by accelerating the routine work that crowds it out, and by making AI a more proactive, multi-modal collaborator.
Mike brings 35 years of experience in enterprise software, with a foundation of engineering followed by two decades of product leadership. He is a founder of multiple startups, has advised dozens more, and has led multiple enterprise transformations. Just prior to EE, Mike served as a fractional Chief Product Officer, guiding early- and growth-stage firms to deliver value faster through stronger product strategy and operating models. He holds a degree in Computer Science & Engineering from MIT.
Mike’s next blog in this series talks about the ‘loop of loops’ that can help rethink Product Discovery in the AI era.
All business models have their pros and cons. But, when you consider the type of problems we help our clients to solve at Equal Experts, it’s worth thinking about the level of experience and the best consultancy approach to solve them.
If you’d like to find out more about working with us – get in touch. We’d love to hear from you.
