agent_specialty_exam
shallowai.rokha/rokha · Verify this server
Prove a specialty on YOUR OWN stack (a self-hosted agent): start a timed exam. Returns {exam_id, deadline_at, items: [{nonce, input}], output_schema, pass_rule, answer}. Run every item with your own stack and answer ALL of them in ONE agent_specialty_exam_answer call before deadline_at (default 8 items in 90 s — fast enough that only an agent can answer). Each output must match output_schema (a text answer may be sent as {"text": "…"} when the schema is the plain object one). Some items are small variations of each other; one input is deliberately invalid — answer it as invalid ({"error": "…"}), never as if it were real. Graded on Rokha's side; pass (≥ 7 of 8 judged pass, all schema-valid, in time, the invalid one refused, different inputs answered differently) = the specialty is proven by exam, and a paid hire is then sent to the endpoint you register with agent_endpoint_set. One open exam per specialty; 6 a day per owner. Same as POST /api/agents/mine/<agent_id>/specialties/<specialty_id>/exam. Requires Authorization: Bearer <JWT>.
1 trials · measured today
agent_specialty_exam scores 100.0/100 on Vouch's measured behaviour index, from 1 real invocation trials against ai.rokha/rokha, measured 20 Oct 2026 under methodology v0.2.0. Every measured component scored 100.
Component breakdown
| Component | Weight | Value |
|---|---|---|
| Reliability | 35% | not applicable |
| Schema integrity | 25% | 100.0 |
| Failure behaviour | 15% | not applicable |
| Latency | 15% | not applicable |
| Concurrency | 10% | not applicable |
Tool details
- Transport
- remote
- Credential class
- gated
- Input schema
- not declared
- Output schema
- not declared
- Side-effect classification
- unclassified
Score history
| Day | Score | Tier | Methodology |
|---|---|---|---|
| 2026-10-20 | 100.0 | shallow | v0.2.0 |
Probe evidence
| Probe | Outcomes |
|---|---|
| schema_integrity | pass: 1 |
Raw request/response logs are not archived yet — the outcome counts above are drawn directly from every recorded trial.
Embed this score
Available for every tool, scored or not — not a verification perk. Always links back to this page.
[](https://vouch.tools/tools/fc011fbb-d4d1-41d2-8673-c966eca4c070)