whatbroke
Diff two agent runs and see exactly what changed
What is whatbroke?
Diffs two agent runs and shows which tool calls fired, how the arguments differed, what each run cost, and where the outputs diverged. Reads JSONL, OpenTelemetry, Langfuse and LangSmith exports. Run it in CI and fail the build on a dropped call.
Screenshots
?
No comments yet. Be the first!
Real conversations about whatbroke on X
Post on X