CAIN-42 CAIN StudioAGENTIC AI 75 · #57
Shopping benchmarks that reward refusing bad purchases
Visa's Agentic Commerce Benchmark tested requirements gathering, evidence, selection and refusal.
Last reviewed 2026-11-11
Agentic AI 75 / #57
2026 status: Released benchmark · Category: Evaluation
The 2026 development
Visa's Agentic Commerce Benchmark tested requirements gathering, evidence, selection and refusal.
The governance gap
Refusal is a control, not a score. A shopping agent should refuse when the mandate, merchant, amount or evidence is missing, and the refusal should be recorded as a decision.
Where CAIN-42 fits: Moat 1 — Trust State
Core question: Who do we trust right now? Evidence-backed trust computed at the moment of the action, never a static badge.
Make refusal a first-class outcome in the mandate engine: missing evidence, unknown merchant and exceeded limit all produce a recorded DENY rather than a best guess.
How the wiring works
- State the purchase requirements and the mandate.
- Verify the merchant and the amount.
- Refuse when evidence or authority is missing.
- Record the refusal and its reason.
What is real today
LIVE A public route in this deployment exercises this mechanism today, within its stated scope.
The mandate demo exercises refusal on fixed carts. It is not Visa's benchmark and does not publish a score.
| Component in this repository | What the module says it is |
|---|---|
cain/commerce/mandate_guard.py | Agent Payment Mandate Guard. |
cain/guard.py | CAIN Trust Fabric - Unified 1-Line Agent Guard Decorator |
cain/runtime/transactions.py | CAIN Sovereign — Machine-to-Machine Transaction Governance (Prompt 7, Phase 18). |
Descriptions are the first line of each module's own docstring, read without importing it. A module path is a pointer into this repository, not a hosted endpoint. Its existence is checked by the test suite; its status for this use is the label above.
Check it yourself
- Run the live payment-mandate demo
/api/v1/payment-mandate-guard/presets - Fire a live decision through the CAIN-42 pipeline
/fabric/try— the same enforcement path every product sits behind.
Commercial package
| Offer | Commerce Refusal Review |
|---|---|
| Buyer | Merchants, PSPs and commerce platforms |
| Price (proposal) | $2,500–$5,000 per review |
| Bundle | Commerce & Payments — Delegated spending with a ceiling and a receipt. |
| Operator stream | Stream 2 of the 10-stream operator playbook |
Fintech, commerce platforms, marketplaces, treasury teams is the bundle buyer. The entry offer for this bundle is Payment-mandate review; browser-agent checkout review; the range is $2,500–$7,500 per review; integration from $10,000. A price on this page is a proposal, not a validated rate, and no customer is claimed.
Buy this as a product or service
CAIN-A75-057 — Commerce Refusal Review DELIVERABLE
A bounded engine run on the buyer's sample: findings, a written report, and a SHA-256 artifact manifest. The manifest is unsigned: it is not a signature and not an attestation.
Kind: Assessment · Price (proposal): $2,500–$5,000 per review · Lead time: 5 business days.
Open the product page · all 75 products
What this page does not claim
What this page is not. CAIN-42 is not affiliated with, endorsed by, integrated into, or shipped with the organisation named in the 2026 item. The item is public context; the page describes how CAIN-42 would govern that class of capability. No page here claims a customer, a partnership, a certification, a patent, or a production integration. Prices are proposals. Built by a three-person team.