Codebase Intelligence & Lineage Engineer
Multi-agent codebase cartography tool that analyzes local or GitHub repositories with Surveyor and Hydrologist agents to produce module graphs and data lineage artifacts.
"Mapped legacy repositories into graph artifacts that agents can query instead of guessing architecture from raw files."

AI agents waste context and hallucinate architecture in brownfield systems when they lack structural maps of modules, imports, SQL transformations, and data lineage.
Built a CLI pipeline that clones or reads repositories, extracts AST/SQL/YAML structure, runs survey and lineage passes, and writes schema-versioned cartography artifacts.
Brownfield Cartographer has two core agents. Surveyor extracts module graphs, PageRank, git velocity, and dead-code candidates. Hydrologist traces data lineage through SQL, Python, dbt, and notebook assets.
Case studies in similar engineering domains.
Event-sourced lending pipeline for document intake, extraction, credit analysis, fraud, compliance, and decision orchestration over an append-only ledger.
Schema integrity and lineage attribution system that turns inter-system dependencies into formal contracts, detects schema/type/statistical drift, and reports downstream blast radius.
PDF triage and extraction pipeline that detects document origin, layout, and domain, escalates extraction strategies by confidence, builds PageIndex trees, and answers with provenance chains.