Back to Browse
Purchase Test Cohort Attribution Detector
x402
Purchase Test Cohort Attribution Detector is a paid API for AI agents from detect.halowerk.com, paid per call via x402, $0.003/call, status unknown (last checked 2026-11-04).
Separates internal acceptance tests, external real usage, and contradictory assignments within an anonymous purchase ledger cohort dataset.
Price / call$0.003
Success—
StatusUnknown
How this service works
Trennt in einem gelieferten anonymen Kaufledger interne Abnahmetests, externe Nutzung und widersprüchliche Zuordnungen.
Output
Returns a structured breakdown of the submitted purchase cohort events, classifying each into internal acceptance tests, genuine external usage, or contradictory/conflicting attributions, along with validation of the supplied scalar claim against the computed external net abstract units (within 1e-9 tolerance).
Example use cases
Filtering QA noise from sales data
“We ran a bunch of internal QA acceptance tests last month and I think they polluted our purchase ledger. I have the anonymous cohort events as arrays and a claim value of 500. Can you analyze them and tell me which events are internal tests vs real customer purchases?”
Validating external usage claim
“My analytics pipeline is reporting a net external unit claim of 8750 for this purchase cohort, but I suspect some internal test events are skewing it. Here are the 80 event arrays — can you check for contradictory attributions and confirm whether the claim holds up?”
Auditing cohort attribution consistency
“I need to audit this anonymous purchase ledger for a client handoff — 30 cohort event arrays with a declared claim of -200. Can you identify any events that have contradictory or inconsistent cohort assignments so I can clean them before delivering the report?”
Technical details
Endpoint
POSThttps://detect.halowerk.com/v1/F-N-PURCHASE-COHORTS/purchase-test-cohort-attribution?utm_source=zero.xyzWhen to prefer
Use this endpoint when you have an anonymous purchase event ledger and need to programmatically distinguish internal QA/acceptance test traffic from genuine external customer usage, especially when cohort attributions may be inconsistent or contradictory. Prefer this over manual filtering or generic anomaly detection when your data conforms to the cohort-event-array format with a scalar claim.
Side effects
- Event arrays exceeding 128 items or 128 elements per array will be rejected with a validation error
- Claim values outside the range -1,000,000 to 1,000,000 will fail schema validation
- Malformed or missing purchase_cohorts object returns a 400 bad request
- Empty event arrays violate minItems constraint and will error
- Payment not provided or insufficient USDC balance returns 402 Payment Required
Input
Schema · Request body
| Field | Type | Description |
|---|---|---|
| artifact | object |
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"