0 active · 0/20 queued
Browser: one start every 1.2 seconds (at most 50/minute), up to 2 active calls and 20 waiting. Shared by examples in this tab. Waiting requests cancel when their run is stopped; a full queue rejects new work without an API call.
Server: 60 requests per rolling 60 seconds and 2 concurrent calls per key, per server instance. Other tabs using the same key share that instance’s allowance. This in-memory safeguard resets on restart and is not a distributed or account-wide quota.
Source: playground policy in lib/requestRateLimit.ts. TypeSafe may impose separate limits. Provider HTTP 429 pauses calls until its reported reset; without a reset time, retry requires your action. HTTP 402 is a budget/billing failure, not a pacing limit. No automatic retries or background replay.
lib/requestRateLimit.ts
Import your key to override the shared server default.
Saved on this browser until removed or site data is cleared. Masked on screen; sent only with Jev requests through this app. The saved value is never displayed.
Describe the case. Add the evidence. Apply your process.
Describe a scenario and see which action follows your process.
A selected playbook, its rules, and the facts you add to the case conversation.
Each turn is evaluated against the playbook. The returned structured decision is interpreted within the configured policy and allowed actions.
A recommended next action and its policy evidence, or a request for more context. Recommendations do not execute business actions.
Select an example and review its rules before starting a case.
Use a sample message or add your own facts to the conversation.
Read the matching rule and add missing evidence when the decision is unclear.
Start a damaged-delivery case with one fact, then add the missing evidence and compare the recommendation.
Recommended actions only. No refunds, fines, bans, or messages are executed.
Start with what you know. We’ll work through the missing details together.