Stack · 2 sessions

reportlab sessions with coding agents

2 sessions on reportlab with a coding agent: the agent failed at least once in 1, and 1 finished without a human stepping in.

More filters →

Claude Code·feature·Web·library1d

Implement Phases 4–5 of TutorDesk AI: auto-grading, multilingual, diagrams

Takeaway: I'd start the next session by having the agent actually run the app and hit the new Modal endpoints instead of just reading code back to itself as a 'sanity check' — it never executed anything for Phases 4 or 5.

11m0interventionsPython gradio modal0 cmt

Codex·debug·Backend·library3d

Fix and harden AI storyboard planner with Modal-hosted models

Takeaway: Next time I'd give the live-endpoint reliability numbers up front — the real fix here only became obvious once we hit MiniCPM and Nemotron live and saw actual timings and malformed output, not from reading the code.

1h 05m1interventionPython FastAPI React0 cmt