Yesterday we landed dynamic model routing in LineageLens: the proxy now classifies requests (simple / standard / complex) using deterministic rules and rewrites the model to a cost-appropriate upstream while recording the decision on every provenance record. The key tradeoff we made: no model fallbacks and no cross-provider routing in v1 to keep correlation and auditability intact. Curious how teams would like routing policies surfaced in CI/PR checks policy-as-code or dashboard toggles?
Been deep in AI-assisted dev work and kept hitting the same wall: something breaks in AI-generated code and there's no way to answer "which prompt wrote this, which model, and what was the context?" Root cause analysis becomes guesswork.
Built LineageLens to fix that. It runs a local proxy on port 8788 that sits between your AI tools and their providers. Every time an AI writes ≥4 lines into your codebase, it captures the exact prompt, the model and tool that produced it (Cursor, Claude Code)
