AutoIndex turns chunking into code optimization: agents write indexing programs for you
CShorten30 · x · 2026-09-08
Weaviate Podcast #143 features Sam O'Nuallain (UMass Amherst) on AutoIndex: instead of tuning chunking as a config, let an LLM write a program for it.
Key ideas:
- Treats indexing as code optimization: an analysis agent and a code agent loop together to write Python "representation programs" that chunk, enrich, and reorganize your corpus
- Every hypothesis must prove validation lift before it survives
- Biggest lesson: "did recall go up?" is useless feedback — giving the analysis agent tools to investigate why a gold document ranked low is what made the system work
A practical engineering paradigm for automated RAG indexing.
Related event: AutoIndex: LLMs Write Code to Automatically Optimize RAG Indexing(7 posts)→
More from coding & agent
- Kolab Benchmark Uses Pro Screen Recordings to Show AI Agents Overestimate Collaboration Quality — minnesotanlp · 2026-10-27
- Dev argues Claude burns far more tokens than GPT models for the same coding work — haider1 · 2026-10-27
- Stop building agents that can't change models: stable contracts, external state, real evals — rseroter · 2026-10-27
- Cheap models can cost more in agent harnesses than frontier ones, researcher warns — vasuman · 2026-10-27
- Kanzo: A 5k-Line Rust Kanban Binary With MCP for Claude Code and Codex — allmudi · 2026-10-27
- 'A human approves everything' is a trap: approval fatigue and how to actually design safe agents — Efistoffeles · 2026-10-27