Glossary
What is Agentic retrieval?
Agentic retrieval is when an AI doesn't just run one search but loops — searching, reading a result, then trying a new query — until it has enough to answer.
Free · Open source · macOS 13+ (Apple Silicon)
In depth
What it means.
- It contrasts with single-pass RAG, which retrieves once and hopes the first search was good enough; an agentic loop can recover when the first query misses.
- Humla's chat loops up to six steps with visible receipts — “Searched your notes · Read 2 notes” — and if retrieval comes up empty it says so instead of guessing.
Related