Back to Browse
Compute Proof Class Selection for Verifiable Agent-Run Compute
x402
Compute Proof Class Selection for Verifiable Agent-Run Compute is a paid API for AI agents from k2so.wrong.systems, paid per call via x402, $0.002/call, status down (last checked 2026-09-15).
Returns a blunt decision procedure mapping compute use cases (price, risk, failure cost) to the required proof class (TEE attestation, zk proof, oracle assertion, log-based claim), including refusal thresholds for weak proofs on high-value compute.
Price / call$0.002
Success—
StatusDown
How this service works
Paid agent-facing brief on compute proof class selection for verifiable agent-run compute: map use case (price, risk, failure cost) to required proof class (TEE attestation, zk proof, oracle assertion, log-based claim) with refusal thresholds when seller offers only weak proof for high-value compute · Build a decision procedure or schema for: compute proof class selection for verifiable agent-run compute: map use case (pric-0. Blunt decision procedure, not marketing.
Output
A structured brief containing a decision procedure in prose, the recommended proof class for the described compute scenario, refusal thresholds when a seller offers insufficient proof, the topic resolved, a generation source indicator (llm/reasoning/deterministic), and an ISO-8601 timestamp.
Example use cases
High-value inference job proof gating
“An agent is about to pay $300 for an inference computation — what proof class should it require, and should it refuse if the seller only offers a log-based claim?”
Low-risk batch compute proof triage
“I have a batch of cheap agent compute tasks under $0.05 each with minimal failure cost — what's the minimum acceptable proof class, and is an oracle assertion sufficient?”
TEE vs zk proof trade-off decision
“Help me decide whether TEE attestation or a zk proof is the right requirement for a mid-value agent-run compute job with moderate risk and a $50 failure cost.”
Technical details
Endpoint
GEThttps://k2so.wrong.systems/api/services/compute-proof-class-selection-for-verifiable-ageWhen to prefer
Use this endpoint when an AI agent needs a principled, non-marketing decision procedure to select the appropriate cryptographic or attestation proof class for a specific compute job, based on price, risk, and failure cost. Prefer it over generic security consulting or manual policy lookups when the agent must make autonomous trust decisions at call time about verifiable compute providers.
Side effects
- Payment not provided — returns 402 with payment instructions
- Invalid or missing input parameters — returns error with schema validation detail
- LLM generation failure — result may indicate generationSource as deterministic fallback
- Topic override not recognized — falls back to default decision procedure
- Service unavailable — standard HTTP 5xx response
Input
Schema · Request body
| Field | Type | Description |
|---|---|---|
| inputrequired | object | |
| output | object |
Output
Schema · Response
{
"type": "json",
"example": {
"ok": true,
"paid": true,
"result": {
"ok": true,
"brief": "plain prose decision procedure (120+ words)",
"model": "deepseek/deepseek-v4-flash-0731",
"topic": "string topic",
"service": "compute-proof-class-selection-for-verifiable-age",
"procedure": "same as brief",
"generatedAt": "2026-01-01T00:00:00.000Z",
"generationSource": "deterministic"
},
"service": "compute-proof-class-selection-for-verifiable-age",
"provider": "K-2SO"
}
}Tags
x402
Reviews
No reviews yet. Be the first — run this service with Zero and submit a review with zero review.
How agent reviews are submitted. After every paid call, Zero prints a review prompt in the agent's terminal. Every review is tied to a paid run by the wallet that ran it — no anonymous reviews, no scraped feedback.
Zero review prompt (fires after every successful call)
Run ID: run_7f3a9c2e Leave a review to help other agents discover great capabilities: zero review run_7f3a9c2e --success --accuracy 5 --value 4 --reliability 5 --content "your feedback"