The short answer
AffixIO helps turn a delegated request into a verifiable yes or no before money, access or a sensitive workflow moves.
AI agent verification
AI agent verification before payments
An AI agent is verified when the system can prove the agent has permission to act, the requested action fits policy and the outcome can be audited without exposing more data than needed.
The commercial problem
Agents can browse, compare and trigger actions, but merchants and platforms still need a reliable way to know whether the agent is allowed to complete the action.
A verified identity is not permission to spend
Verification answers a specific question about a specific request. Recognising the agent does not establish that its user approved a purchase, that a merchant accepts its credentials or that a bank will authorise payment. Those checks have different owners.
Example: a delegated purchase with a GBP 100 limit
This is an illustrative policy example, not a live AffixIO response. A user approves one purchase of office supplies from a named merchant, with a total limit of GBP 100 including delivery and tax, valid until a specified time.
- Within scope: the agent requests GBP 86 from that merchant before expiry. If identity, current consent and all other required checks pass, the application may proceed to payment authorisation.
- Outside scope: delivery changes the total to GBP 104. The original approval does not cover the new amount. Stop and request a new approval.
- Insufficient evidence: the consent service is unavailable. Do not treat an unknown result as permission. Pause or route the request for review.
- Revoked permission: the user withdraws approval before checkout. A previously successful check must not override the current revocation state.
What evidence should travel with the decision?
Keep an agent reference, consent reference, intended action, merchant, total and currency, policy version, decision time and evidence reference. Protect those references as appropriate for your system. A signature can help establish the origin and integrity of a result; it does not make incorrect inputs true.
For the next step, read how to capture and recheck user consent or the merchant checkout integration sequence. Use the SDK documentation for supported methods rather than treating this example as an API contract.
Where AffixIO fits
AffixIO sits before the action. It helps your application ask whether the user, agent or delegated workflow is allowed to continue, then returns a decision your product can enforce.
Agent identity
Identify the software actor, session, user mandate or delegated workflow that is asking to act.
Permission check
Check whether the action matches the permitted scope, such as amount, category, merchant, location, account or time.
Decision proof
Return an enforceable result with evidence, not a new pile of raw personal information.
Audit readiness
Keep a record that can be inspected later when a support issue, chargeback, compliance review or dispute appears.
AffixIO role
AffixIO is not the shopping agent or the payment provider. It is the proof layer before the controlled action.
Designed for buyers who need trust without data sprawl
Use AffixIO when a checkout, platform, marketplace, API, internal tool or AI agent needs a clear permission result, signed evidence and a cleaner privacy posture. The value is not another dashboard full of personal records. The value is a decision with proof behind it.
Questions this page answers
Answers about verification, payment authorisation and implementation.
How do AI agents get verified before making payments?
They need an identity context, a delegated permission, a policy check and a signed result that the merchant or application can enforce before checkout.
Does verification mean the agent is trusted forever?
No. It should be checked per action, per session or per policy boundary.
Does AffixIO replace payment authorization?
No. AffixIO helps prove permission and eligibility before the payment provider authorizes or declines the transaction.
Put a proof step before the risky action.
Start with the SDK, map the decision you need and connect the result to the place your product already enforces access, checkout or policy.
BoundProof Agent
Give every AI agent its own proof area before it acts.
Provision a persistent BoundProof Agent, check its proof allowance and give a reviewer a scoped AffixIO Hub code. Trial and paid access follow the current billing status of that agent area.
- bpa_ agent key first. SDK key access depends on an active trial or subscription licence.
- Authorised payment. An authorised agent can use the documented API payment flow. Human payers use hosted Stripe Checkout. Payment-provider authentication may still be required.
- Scoped Hub view. The BP code opens only that agent's own area, usage and proof status.
Starter paid access
From £19/month
Provision the agent, check its licence and allowance, then request an SDK key through the documented flow.
Source-backed checks before an agent acts
A permission decision is stronger when the condition can be checked against a configured record and written into evidence. AffixIO lets an application reduce that check to a clear yes, no or review result before it authorises the next step.
Check the condition
Evaluate the fields your policy needs, such as consent, amount, merchant, eligibility or account status.
Keep the decision useful
Return an outcome your checkout, API or tool gateway can enforce without exposing more source data than required.
Verify the record later
Write signed evidence that can be inspected during support, compliance or dispute review.