Blog
Engineering notes on durable agent orchestration — the unglamorous parts that make unattended LLM runs survivable.
AI agent guardrails are prompts. Safety invariants are guarantees.
Every agent framework ships 'guardrails' — instructions the model is asked to follow. But an agent that can rewrite its own tests and approve its own work needs more than a polite request. Structural safety means the unsafe transition is impossible: the transaction rolls back.
Replay-deterministic LLM agents: why your agent runs need a ledger
LLM agent frameworks obsess over prompts and graphs while ignoring the unglamorous part: what happens when a 40-minute run crashes at minute 35. The answer is older than AI — make the run a transaction.