🚀 Just shipped: AI prompt/model management, built right into your @GitHub repo. Version prompts, test 40+ models, and run evaluations all in the same place you ship code. Here’s a (short!) demo from our launch at @Microsoft Build: TLDR:.– Version.

Really cool GitHub Models use case from @slicknet that's especially helpful for OSS maintainers - Given a GitHub repository and release, it creates a social post summarizing the key changes and improvements: .

"When intent approaches perfect clarity, resistance approaches zero." . Great line from a substack someone just sent me regarding AI agent design, but I can also see this in a textbook about product management ♥️.

I vibe-coded an AI-powered GitHub Action that:.- Scrapes Discussions daily.- Uses GitHub Models to classify posts.- Auto-opens issues for bugs. Copy it to catch community bugs early - and plug AI into your workflow with GitHub Models! . 👉

RT @GitHubNext: We're excited to share our new project at GitHub Next called "Continuous AI". Some details in thre….

“Continuous AI” is my favorite new industry term. ✨ It means any use of automated AI to support software collaboration, on any platform. Great list from the @GitHubNext team of "awesome" cross-industry examples:.

Props for the awesome demo video to @damovisa! . Read more:

GitHub's AI developer tools now support pay-as-you-go or bring-your-own-key. Pay us. Pay OpenAI. Pay Azure. Just don’t ship untested AI outputs 🙏

RT @upscaleconf: 🎙️ Interview with Kate Catlin (@Kate_Catlin), Product Manager at @github, hosted by Verena Puhm (@verenapuhm) at #UpscaleC….

Just ran into this awesome video from @aiDotEngineer on "7 Habits of Highly Effective Generative AI Evaluations" - that was so well spoken and highly educational!

Level up your AI security skills! `Secure Code Game: Season 3` just launched! And it's powered by @github Models on the backend :) . A fun way to learn how to build cool AI stuff and not get hacked 👾.

If you're just getting into the space, check out @github's new lightweight evaluations tooling, perfect for getting started:

Awesome quote on the importance of ✨evals✨ in AI products:. "I think this [evals] is literally where the rubber meets the road. If you are out there. understanding that user better than anyone else and having the software actually work for those people, THAT's the moat.".

HUGE thanks to @upscaleconf for having me as a speaker this year, and to @verenapuhm for the great convo on the livestream!. Loved demoing @GitHub’s new AI developer tools (see the “Models” tab!) and digging into my personal product management philosophy.

RT @mariamsulakian: @1adrianpierce @iwebst Used promptfoo for a while before moving to our own eval stack. Now we’re leaning into GitHub’s….

RT @ashtom: ~~America’s~~ GitHub’s Next Top Model (Update): You can now integrate GitHub Models directly into your repo to compare model op….

RT @tymzap: Well-defined prompts can save hours (if not days) of work and it's good to see they start getting the same treatment as code, i….

YES! A new suite of AI developer tools just landed in your @github repo under the `Models` tab. We offer lightweight prompt management, quantitative evaluations, and model comparisons. It’s early and evolving, so kick the tires and tell us what to build next!.

Loved working with @fkadev on this! . Start with a prompt on add the .prompt.yml file they generate to your repo, and build the future! . More about the new AI dev tooling repo integration: .