(no title)
dipeshsukhani | 2 months ago
Concretely, we: - Break each person’s day into deterministic, measurable tasks with expected time cost and explicit test/code criteria in the repo. - At EOD, run the updated repo through an AI agent that checks for those tests/changes, scores how much of each task was actually completed, and produces a per‑person and team summary that replaces the verbal stand‑up.
Happy to elaborate on this more if you would like.
No comments yet.