The prompt
Prompt
OUTLINE ONLY — Not a production recipe.
When to use: agent loop needs a typed next step.
Inputs: goal + recent tool results as state.
Question sketch:
- next: Choice among allow-listed tool ids OR {continue, retry, ask_user, stop}
- needs_confirm: Boolean
Confidence policy: low confidence → ask_user.
Links: TypeSafe launch post; Gateway evaluate docs.
Needs access to: typesafeagents
How it's set up
Keep the allow-list and thresholds in one file. Fan out related Booleans in the same evaluate call.
Not a production recipe.
Why it works
System One Choice cannot leave your option set — useful when LLM agents invent tool names.
This use case was collected from the public Jev community and is credited to its original author. Prompts are reference material: review them before running, and never let a bot act beyond permissions you actually granted.