Eval Case Generate

Eval case generator for an agent or LLM task: describe the task and get back a draft llm eval dataset of {input, expected, rubric} cases spanning typical, edge, and adversarial scenarios.

Overview

Eval case generator for an agent or LLM task: describe the task and get back a draft llm eval dataset of {input, expected, rubric} cases spanning typical, edge, and adversarial scenarios. Pass example cases to steer style, and set n for how many to generate (default 8, max 20). Every case is labeled a candidate needing human review, not validated ground truth: this drafts a first pass at agent test cases, it doesn't certify them. Use it as an agent regression tests starter, an eval dataset generator for a new task, or a quick way to seed a rubric-graded benchmark before a human tightens it.

Endpoint

Method	Endpoint	Price	Description
POST	/v1/marketplace/api/eval-case-generate	$0.023	Invoke Eval Case Generate (Llm) and return the upstream response.

How to call it

Requests are paid per call over the x402 protocol. Call the endpoint, receive a 402 Payment Required quote, then repeat the request with the signed payment header. The SDKs do both steps for you.

# 1. Ask for a quote
curl -i -X POST https://api.jarvisclaw.ai/v1/marketplace/api/eval-case-generate \
  -H 'Content-Type: application/json' \
  -d '{}'

# 2. Pay it (the SDK signs and retries for you)
curl -X POST https://api.jarvisclaw.ai/v1/marketplace/api/eval-case-generate \
  -H 'Content-Type: application/json' \
  -H 'X-PAYMENT: <signed-payload>' \
  -d '{}'

Open in the marketplace