writing

Notes from the desk

Things worth writing down.

writing · 3 min

Multi-agent systems don't fail. They drift.

A2A solves how agents talk to each other. It doesn't solve how they stay pointed at the same outcome. Each agent can do its job correctly and the system still produces the wrong result.

#agentic#llm#workflow-orchestration
writing · 1 min

Make the model show its work

Reasoning chains aren't just for accuracy. In an enterprise system they're how you earn trust, debug failures, and catch a model doing something it was never asked to do.

#llm#explainability#rag
writing · 1 min

Teaching a RAG pipeline to pick the right document

Generation quality is the part everyone demos. Retrieval quality is the part that decides whether the demo was a lie. Notes on auto prompt-tuning for document selection.

#rag#prompt-engineering#llm
writing · 1 min

From text to 3D motion: generating sign language

What I learned building SIGN-LLM: why sign-language generation is really a data problem, and why separating 'how to represent motion' from 'how to produce it' is the trick that makes it work.

#computer-vision#generative#llm
writing · 1 min

When the search quietly regressed

Search quality rarely fails loudly. It drifts. Notes on benchmarking, fluctuation analysis, and root-cause work on a recommendation and search pipeline.

#search#evaluation#data-engineering
writing · 1 min

The feedback loop is the product

A search system you can't measure is a search system you can't improve. Notes on building human-in-the-loop feedback for an enterprise RAG pipeline.

#search#rag#evaluation#human-in-the-loop
writing · 1 min

Reading documents in a clean room

Doing OCR and entity extraction on health records inside a Trusted Research Environment, where the data can't leave and most of your usual tools can't come in.

#computer-vision#ocr#ner#security