Finding
What goes wrong, how often, where, the suspected cause, a proposed fix and the evidence.
Why. A short ranked list is readable; a dashboard isn't an answer.
Boundary. A person sets its status.
Cross-run analysis
Analyze thousands of AI workflow runs to find issues, their causes and replay-tested fixes.
Prevents: Outputs slowly converging, silent repairs, zeros that mean 'failed' and cost creep going unnoticed because no single trace looks broken.
Why it exists
Workflow problems that only exist across many runs.
Scope. Reads records and writes reports; never changes a workflow.
Five-minute orientation
pip install "git+https://github.com/honeworks/hone-lens"
Real output
Architecture
A funnel: statistics over all runs, embeddings of all outputs, an LLM only for descriptions and hypotheses within a budget, then replay tests through a Replayer port.
Core concepts
Operations
`hone-lens ingest / analyze / findings / explain / test / report / set-status`.
Current boundary
Alpha. No multi-step replay through a workflow runner, watch mode or image/audio analysis yet. Cause-finding depends on what was recorded.
Near-term roadmap. Follow the design history in design/changes/.
What it implements
Engineering checklist
Need the control, not just the component?
The repository exposes the mechanism. Production work is defining the permissions, data, failure costs, evidence, and owners around it.