Conference season is back, and so are the real conversations. In this episode, Peter Maddison and Dave Sharrock catch up after a busy stretch of travel and dig into something Dave has been road-testing at conferences: why most people given access to AI tools freeze up, and what actually helps them move past that.

Dave ran a workshop at the Global Scrum Gathering in Vancouver for non-technical roles - product managers, Scrum Masters, agile coaches - people who've been told "use AI" but have no clear picture of where to start. What he found is that the problem isn't motivation or technical ability. It's the lack of scaffolding. Give people the right structure and the right room to experiment, and things shift pretty quickly.

The conversation then moves into multi-agent systems - how Dave's team built a group of agents that continuously refresh the workshop itself based on current thinking. Peter adds his own take on testing these systems with personas and automated quality evaluation. It gets a bit technical, but in the best way.

This is a good episode if you're thinking about how to help your organization actually use AI, not just adopt it on paper.

Key Takeaways:

• Context beats generic. Prompts work when they're specific to your role and your actual problems. A product manager needs product management context, not a one-size-fits-all example.
• Think in teams, not steps. Multi-agent systems work best when you treat them like a team reviewing an artifact, each agent checking for something different, rather than a linear build process.
• Don't assume everyone gets it. The gap between people who use AI daily and people who tried it once and gave up is wider than most of us realize. Getting both groups in the same room is where the real learning happens, for everyone.

Have a question or something to add? Reach out at feedback@definitelymaybeagile.com or find us at definitelymaybeagile.com. And if you're finding the show useful, subscribing and leaving a review goes a long way.

Most organizations think they're doing AI. They've bought the licenses, rolled out the tools, and told the team to start using Copilot. But adding AI on top of a 40-year-old process isn't transformation. It's decoration.

Andre Kaminski, Director of Advanced Technology Solutions at WorkSafeBC and author of "The AI-Native Software Development Lifecycle," joins Peter and Dave to talk about what it actually means to rebuild your delivery process around AI, not just bolt it on.

They get into why optimizing code generation alone is the wrong focus, what the six phases of an AI-native SDLC look like in practice, and why the biggest challenge isn't the technology at all. It's the identity shift that comes with it.
If your organization is asking "which AI tool should we use?" this episode will help you realize that's probably the wrong question.

In this episode:

• Why AI-augmented and AI-native are very different things
• The compounding learning effect and why early adopters are pulling further ahead every month
• What prompt architecture actually means and why it matters more than code
• How to think about governance when prompts become your new source of truth

Want to keep the conversation going? Drop us a line at feedback@definitelymaybeagile.com or find us at definitelymaybeagile.com. If this episode got you thinking, share it with someone who needs to hear it.

Agreeing on an idea doesn't mean you both understood the same thing. Dave Sharrock and Peter Maddison dig into why shared context breaks down in practice, and how AI makes that problem harder to ignore.

This week's takeaways:

• Intent is always imperfect. Define how you'll validate it, not just what it is.
• Ambiguity in context isn't a bug. It's necessary. Validation is how you confirm you're aligned.
• Drive down the cost of validation, not just the cost of building.

If this landed, share it with someone navigating the same tension. And reach out at feedback@definitelymaybeagile.com - we read everything.