Grep or Embeddings? Agentic Search Over Company Documents — George He, LlamaIndex

Claude Code's grep-only approach suits small local code but breaks on millions of permissioned, multimodal documents. This shows how to give agents hybrid retrieval as a compass, then listing, filtering, grep and read tools to ground answers.

• agent harness — The scaffolding around a model that turns it into a working agent — the loop, the tools it can call, and the rules for when to stop.
• multimodal — A model that works with more than text — reading images, audio, or video, and sometimes generating them too.

• videoFrom 36% to 100%: How Self-Improving Agents Write Their Own Skills — Rafal Wilinski, Runlayer
• videoIs Speculative Decoding Worth It? Profiling vLLM on NVIDIA Blackwell — Akamai
• videoThe 6 Pillars of an Agentic Harness for Production — Varun Krovvidi, Resolve AI
• videoEvery AI Company Is Accidentally Building a Bank — Dor Sasson, Stigg

• videoBuilding the Document Context Layer for AI Agents — Jerry Liu, LlamaIndexAI Engineer
• videoAgentic Search vs Vector Search for Coding Agents: We Ran the Eval — BraintrustAI Engineer
• videoFrom Ingestion to Agents: How AI Teams Build on Document Intelligence — Adit Abraham, ReductoAI Engineer

Checking sign-in…

Loading comments…