API · Last updated 2026-09-21

Jev API action fields

A Choice option may be named like an action (approve_transfer). TypeSafe still only returns a label and probabilities. Your code calls the bank API — or does not. There is no documented action execution field.

This page is for builders who searched an extra “endpoint” name while wiring Jev / System One. jev.pro is an independent unofficial field guide — not affiliated with TypeSafe AI. We do not sell or issue keys. Confirm first-party routes on docs.typesafe.ai/api.

The public API reference documents one evaluation route — POST https://api.typesafe.ai/v1/systemone — plus GET /v1/models. This title is not a separate first-party URL in that reference. Treat the capability as something you implement around the official call.

Steps

1. Design the action space first.
2. Map labels → handlers in code, including abstain.
3. Gate on confidence / Noul bands before side effects.
4. Log the verdict separately from the raw choice.

Map onto the official POST

Answer remains choice + probabilities + confidence (or noul only). No executed: true from TypeSafe. No /v1/actions. Choice options are unordered, max 255. Question ids are not sent to the model and are not function names the host will invoke.

A label is not a permission check. An agent that executes tools because the option looks like a function is doing LLM tool-calling, not System One. Schema-safe ≠ authorized. Pin jev-1.13.0 before you bind handlers; aliases currently resolve there — confirm.

Documented errors: 401, 422, 429, 529. Official SDKs retry 429/529. Retries may repeat the judgment; they must not repeat the transfer — see idempotency. You compute hold — human review. Vendor-claimed token price still applies to the judgment only.

When not to name options like RPCs

Prefer nouns a reviewer can apply (approve, hold, escalate) over POST /transfers. Keep the HTTP verb in your handler table.

Pitfalls

• Believing a label is a permission check.
• Letting an agent execute tools because the option name looks like a function.
• Looking for executed on the response.
• Calling /v1/actions.

See also

• API hub — labels only
• Action space — design the set first
• Confidence-gated routing — floors before side effects
• Response format — what comes back

FAQ

Is /v1/actions documented?

No.

Can Jev return a tool-call JSON blob?

That is LLM tool-calling, not System One.

Human review field?

You compute hold — human review.

Does a 200 mean the payout happened?

No. 200 means you received a judgment.

What this page does not claim

• Official TypeSafe status, logos, or support.
• That jev.pro sells, issues, or proxies API keys.
• Extra first-party HTTP routes beyond POST /v1/systemone and GET /v1/models unless the API reference lists them.
• Invented latency SLOs, search volume, or unofficial prices. List price and rate limits are vendor claims — confirm on models.
• That a schema-constrained answer is automatically factually correct.

Disclaimer

This is an independent unofficial site and is not affiliated with TypeSafe AI; official documentation is available at https://docs.typesafe.ai. Never treat jev.pro as TypeSafe official documentation. We do not sell, issue, or proxy API keys.