Launching today
Pheebs
Measure how engineers and teams actually work with AI
60 followers
Measure how engineers and teams actually work with AI
60 followers
Measure how you and your team actually work with AI coding agents. Pheebs is an open-source AI telemetry tool created by Eversynced. It sits quietly inside Claude Code, Cursor, and Codex via hooks, capturing lightweight interaction signals: the shape of the session, not its contents.
@pratesd love that you said out loud that being vulnerable about AI skills is hard. that's the real reason people stay stuck, and most tools skip over it 😊 open source is a nice touch too
Hi Pheebs team! I really liked the idea of seeing how often outputs get modified and whether those lead to cost-savings. And also running tests before commits. A few comments / suggestions. 1) Are those metrics shown in the images you have for the Overview? And also, for a given company, is there a way to generate a baseline for a developer's activity that the other developers could follow? for example, maybe you don't need the AI to run and analyze tests after every commit, and only do it before pushing the code? (just thinking out loud for a counter example). Or maybe for a given project, it is better NOT to push back on the code generated by the agent?
2) What do you think of a summary page that shows the recommended steps? You might already have it. I'm only going by the images in the overview.
@sara_ford_goog Hi Sara, thank you so much for your comment!
1) Yes, those are the metrics Pheebs provides in the Insights feature. There's currently no way for a company or manager to set a baseline - that could be an interesting feature! What we currently do is show team median as a way to establish a baseline. In the future, we'll also show industry benchmarks based on real data. Specifically on pushback, the goal is not to encourage teams to pushback on all outputs, but to encourage a healthy rate that results in a high quality AI practice. Same with other rates, we'll want to establish a ratio that's healthy and results in more quality.
2) We actually offer the recommended steps as part of our AI Enablement Assessment service (powered by Pheebs, of course)! As we get more feedback from companies on Pheebs as a product we'll continue to expand it and possibly create a managed offering.
I enjoy the overall idea. I think a lot of organizations are struggling to figure out how to track this information and ensure that they are getting the value that they thought they would for AI. Does it simply create a report or does it help in creating restrictions, identifying patterns, etc.?
@cloudalchemist Hi Jay, thanks a lot for your comment - and we completely agree!
Currently Pheebs captures the data and provides analytics using the proposed AI Proficiency Model (repertoire + judgement). To your question, it currently doesn't help creating restrictions specifically, however all reports (engineer and team views) help with identifying patterns and where teams should act with more intention e.g. the team is lacking on artifacts usage let's stand up a skills repo and evangelize it, or the team is lacking on evals let's invest in verification harness, etc.
Congrats Davi! that's awesome
@german_merlo1 Cheers!