Highlights from the first informal AI Show + Share - spec driven development, Lovable prototyping, and greenfield AI workflows
Had a good first informal AI Show + Share yesterday. I think for any future ones if there's interest I'll split into two different tracks:
I talked about my experience and how impressed I am with github's speckit framework for spec driven development, and Matt Lievertz discussed his lighter weight approach for spec driven development
Jeff Wraley showed off what he was building in Lovable as a non technical founder and how he was doing his first real merge request using Devin
Justin Lacey discussed how he was trying to find the right balance of prototyping vs. engineer hand off and how the role of front end engineers are evolving now and what might need to change - and whether the prototype should become the actual MVP
Francois-Xavier 'FX' Jammes discussed exploring automation of workflows generally and we discussed as a group whether we were seeing more "brownfield" automation of existing work vs. "greenfield" workflows where AI makes things feasible that weren't before - the group seemed to agree that greenfield workflows have a lot of opportunity that may be under-discussed.
Thanks to all who could make it!
An agent-first, human-friendly knowledge base is one of the most impactful tools in my day to day work, yet sharing and maintaining that context across a team is still surprisingly hard.
Vibe coding is perfect when you're still finding out if anyone wants your thing. Once real usage and real money show up, agents make software engineering matter more, not less.
Persona-style agents are fun to name, but juggling Claude Code, Codex, ChatGPT and more calls for a single interface. Right now the answer might be to build it myself: a filterable Kanban board with a direct line to each agent.
Get More Like This
Follow along as I build and share what I learn
Found this helpful? Share it with your network!