whatbroke is an open-source developer tool designed to help developers inspect and debug AI agent workflows. By diffing two separate agent runs, it allows users to see exactly what changed between execution cycles.
The tool provides detailed visibility into the operational behavior of AI agents by showing which tool calls fired, how the arguments differed, what each run cost, and where the final outputs diverged. Additionally, whatbroke is built to fit seamlessly into modern development workflows; it can be integrated directly into your Continuous Integration (CI) pipeline to automatically fail builds when a critical call is dropped.
To make ingestion easy, whatbroke natively reads data from multiple standard formats and observability platforms, including JSONL, OpenTelemetry, Langfuse, and LangSmith exports.
whatbroke is an open-source developer tool that compares (diffs) two AI agent runs to identify exactly what changed, including tool execution, argument differences, costs, and output deviations.
whatbroke can read and process exports from JSONL, OpenTelemetry, Langfuse, and LangSmith.
Yes, you can run whatbroke within your Continuous Integration (CI) environment and configure it to fail your build if a dropped call is detected.
0 community reviews for whatbroke
Help the community by sharing your experience. Your review helps others make better decisions.
Serial Builder.
