Aneeq Khatri
Governed RAG where weak retrieval refuses instead of guessing, applied to a finance policy manual
- Python
- LangGraph
- FastAPI
engineering portfolio
16 projects. Built to be checked.
Governed multi-agent systems, proven where a wrong number costs the most. Every project gives the problem, the architecture, the decisions and their alternatives, and the evaluation method with its numbers.
All project data is synthetic. Individual projects document their datasets. Available walkthroughs are collected on the demos page.
Production agent failures turned into versioned eval cases, applied to finance agent traces
- Python
- OpenTelemetry
- LangSmith
A prompt-injection corpus with benign twins, so it measures discrimination not blocking, applied to finance documents
- Python
- Promptfoo
- PyRIT
No value the LLM produces can reach a policy decision, applied to invoice approval
- Python
- LangGraph
- FastAPI
Analysis with receipts, where the model never sees the source data, applied to financial statements
- Python
- LangGraph
- FastAPI
Confidence, gate, learn. The simplest honest agent loop, applied to expense categorisation
- Python
- LangGraph
- FastAPI
Vision extraction checked by arithmetic, with bounded repair and a second check on the repair itself
- Python
- Pydantic
- OpenAI
A monthly finance pack narrated by a model that cannot invent a number, applied to management reporting
- Python
- FastAPI
- LangGraph
built, not yet captured
These run, and are written up in full. They join the grid above once their screens have been recorded.
The full set of repositories is on GitHub.