Agent State Machines: adding deterministic scaffolding to tame nondeterministic LLM agents
blaizedsouza · x · 2026-11-04
Josh Rosen published "Agent State Machines: Building Deterministic Scaffolding for Agents," arguing agents need deterministic scaffolding.
- Without a state machine, what actions an agent takes and when are entirely at the mercy of model nondeterminism
- Explicit state transitions constrain the workflow, so the model only decides within controlled nodes
- Useful for building predictable, auditable agent workflows
More from coding & agent
- ThunderAgent merged into LLM-D: 2x agent serving throughput, TTFT from ~50s to 2-4s — simran_s_arora · 2026-11-04
- Agents pass the test but fail the job: the requirement gap and the model gap — bigdata · 2026-11-04
- Does that new prompting trick actually work, or just look better? — jimmykoppel · 2026-11-04
- Vercel launches Security Review in public beta, free until Nov 10 — cramforce · 2026-11-04
- QuickProof: formal verification for C with specs written as plain C tests — thomasahle · 2026-11-04
- Project Moah: Open-Source Memory Linker That Gives AI Agents a Brain — starcount_games · 2026-11-04