OpenSpec - with Tabish Bidiwale

In this episode, Gui Ferreira is back for the second of two episodes we recorded back-to-back. In the last episode we did a deep dive into Claude Code - and this time we're talking about using coding agents for things that aren't code! We chatted about pointing an agent at a folder of markdown files, daily briefs and personal podcasts, running coach agents built on Strava and Garmin data, an Obsidian vault as a "life agent", and building personal software just for yourself - and when it's worth turning into a product. We also got into what all of this means for hiring, system thinking, and the flow state and fatigue of juggling multiple agents.For a full list of show notes, or to add comments, please see the website here

In this episode, I was joined again by Gui Ferreira - who was last on the show back in episode 78 talking about goals and time management. This time we're talking AI, and specifically a deep dive into Claude Code, which Gui has two Dometrain courses on! We did a lightning round of our favourite Claude Code features and tips - including /goal, dynamic workflows vs /batch, auto mode (and the surprise behaviour change that caught me out!), Ctrl+G and Ctrl+S, voice mode, /btw, rewinding, path-scoped rules, and /simplify. We recorded two episodes back-to-back, so keep an eye out for the next one, where we chat about using coding agents for things that aren't code!For a full list of show notes, or to add comments, please see the website here

In this episode, I was joined by Matt Pocock - creator of Total TypeScript, and the author of the wildly popular mattpocock/skills repo of agent skills, which work with any agent or model. We deliberately agreed beforehand not to plan this one, and just let the conversation go wherever it wanted to! We chatted about his grill-me and wayfinder skills, the death of tactical programming, the "smart zone" and the "dumb zone" of context windows, whether sprints still make any sense, and the era of personal software.For a full list of show notes, or to add comments, please see the website here

In this episode, I was joined by Tabish Bidiwale, the creator of OpenSpec! As a daily user (and big fan) of OpenSpec, this was a great honour to geek-out about it with the creator, and chat in general about coding with AI agents.For a full list of show notes, or to add comments, please see the website here

This was another live audience recording, hosted once again at the DDD South West conference in Bristol (UK) - two years on from the first live panel we recorded there. I was joined by a panel of speakers, and this time the conversation focused specifically on what AI means for software developers. After introductions, we dug into whether AI is going to take our jobs, how much code we actually still hand-write, whether (and how) we review every line of AI-generated code, what's going to happen to programming languages, and what advice the panel had for developers just starting out.For a full list of show notes, or to add comments, please see the website here

In this episode, I was joined by Chris “Woody” Woodruff to chat about a simplicity-first approach to software architecture. Chris has a book coming out on this topic, and we discussed why simplicity should be the default.For a full list of show notes, or to add comments - please see the website here

In this episode, I was joined by both Irina Dominte and Jonathan Tower to chat about the .NET Foundation. They both recently ran for the .NET Foundation’s board of directors, and were elected! 👏 We chatted about their experiences running for the board, what the election process was like, and their initial experiences as board members.For a full list of show notes, or to add comments - please see the website here

In this episode, I was joined by Debbie O’Brien to chat about Playwright - Microsoft’s open-source end-to-end testing framework. I’m a huge fan of Playwright, so I was really excited to have this chat with Debbie. We covered a lot of ground, including features such as Codegen, Trace Viewer, and UI Mode. We also spoke a lot about AI - including the exciting Playwright MCP Server which enables AI agents to automate browser interactions!Debbie has been an integral part of Playwright as a Principal Program Manager at Microsoft and has led the Playwright community, shaping much of what Playwright has become today - driving a lot of the features mentioned above. She’s also a Google Developer Expert in web technologies, Nuxt Ambassador, and is a former Microsoft Most Valuable Professional in developer technologies, Media Developer Expert and GitHub star alumni.For a full list of show notes, or to add comments - please see the website here

In this episode, I was joined by James World to chat about AI for developers. We covered a lot of general AI chat - from using it to quickly knock up tools, to spec-driven development, and much more. We also discussed the Microsoft Agent Framework - a new open-source framework for building AI agents and multi-agent workflows.James World is a seasoned technology leader and Solution Architect with over three decades of experience building and guiding software solutions across the financial and enterprise sectors. He’s a passionate polyglot programmer, with deep expertise in C# and the Azure ecosystem, including years spent learning and teaching at Microsoft where he was a consultant advising customers building solutions on the Microsoft stack. Outside of hands-on engineering and architecture, he loves exploring continuous learning, mentorship, and ways to help teams level up their craft - topics he’s shared on The Unhandled Exception Podcast and in tech communities around .NET and cloud computing.For a full list of show notes, or to add comments - please see the website here

In this episode, I was joined by Jeffrey Palermo to chat about AI-driven development and DevOps. We discussed how AI is changing the way we write software, and the importance of having mature DevOps processes in place (eg. good tests, CI pipelines, and specs) before we can properly start leveraging AI to write features in a reliable and consistent way.Jeffrey Palermo is the host of the Azure & DevOps podcast, Founder and Chief Architect of Clear Measure, a long-time Microsoft MVP, tech speaker, book author, and more!For a full list of show notes, or to add comments - please see the website here