Lats
# Layer 15: LATS (Language Agent Tree Search)
**Research:** Koh et al. 2024 — "Language Agent Tree Search" (ICML 2024)
**Impact:** 94.4% on HumanEval (GPT-4), +14% over baseline
## Technique
Monte Carlo Tree Search applied to LLM reasoning. Explores multiple solution paths with backtracking, evaluation, and reflection. The most powerful (and expensive) technique — use only in /omni-plan mode.
## LATS Protocolwhen to use it
Community prompt sourced from the open-source GitHub repo ShaheerKhawaja/ProductionOS (MIT). A "Lats" style prompt — adapt the placeholders and specifics to your task. Imported as-is and not independently retested here, so check the output before relying on it.
tags
productivitycommunitydeveloper
source
ShaheerKhawaja/ProductionOS · MIT
more in Productivity
Productivity✓ tested
Summarize a doc into decisions & actions
chief of staff who extracts what to DO, not just what was said
Productivity✓ tested
Draft a reply to a hard email
calm, direct communicator who de-escalates without caving
Productivity✓ tested
Turn a brain-dump into a weekly plan
planning coach who protects your focus, not just your calendar