Reference · updated 8 September 2026

The comparison

Four tables, on four axes, using the same criteria each time. They are not rankings: the things compared here are mostly not substitutes for one another, and a serious deployment uses several at once. The point is to make the trade in each case legible, so a choice can be made deliberately rather than by default.

This page is revised as the field moves — it is the part of the hub most likely to be wrong first. Where an approach simply does not address a criterion, the cell says so rather than scoring it low.

Spend controls

What can each mechanism actually constrain, and where is it enforced?

Every approach to bounding an agent's spending sits somewhere on a trade between expressiveness and unavoidability. Controls attached to an instrument are enforced whether or not the agent cooperates, and can only express what the authorisation message carries. Controls evaluated before the payment can express anything you can compute, and are only reached if the agent calls them.

A serious deployment uses both: a policy that can express the real rule, and an instrument-level cap that holds when the policy is bypassed.

ApproachPer-transaction amountCumulative budgetCounterpartyPurposeTime windowEnforced whereBypassable by the agent
Virtual / vendor-locked cardYesCard limit onlyMerchant lockNoCard validityCard authorisationNo
MCC blocklistNoNoCategory onlyApproximateNoCard authorisationNo
Agentic token (network)YesUsage rulesMerchant, categoryNoTimeframeNetwork authorisationNo
Shared payment token (ACP)YesNoOne merchantNoShort expiryPayment providerNo
AP2 mandate constraintsYesAs issuedAs issuedPartiallyAs issuedRelying partyNo
Policy engine (pre-transaction)YesYes, statefulYes, with historyYesYes, with hoursBefore executionYes, if not called

Scroll the table sideways for the remaining columns.

Reading it

The two right-hand columns are the whole argument. Instrument-level controls cannot be bypassed and cannot express purpose; pre-transaction policy can express purpose and can be bypassed. Neither is sufficient alone, and the failure modes are different enough that having both is not redundancy.

The 'cumulative budget' column is where most single-mechanism designs fall down. A per-transaction limit and a merchant lock still permit the same correct-looking payment forty times.

Payment credentials

What is handed to the agent, and what does a leak of it cost?

The credential question is really a blast-radius question. Everything here is an improvement on giving an agent a card number, and they differ in how much an attacker gains by stealing one.

ApproachWhat the agent holdsScopeLifetimeLoss if leakedCarries policyStandardised by
Card on fileCard credentialsAnywhere the card worksUntil expiryFull card limitNo
Virtual cardA surrogate card numberOne vendor, one limitUntil cancelledThat card's limitLimits onlyIssuer products
Agentic tokenA network tokenUser, agent, merchant, categoryPer token rulesBounded by token rulesYes, within formatMastercard Agent Pay
Shared payment tokenA delegated payment tokenOne merchant, one amountShortOne transactionAmount onlyACP delegate payment
AP2 mandateA signed verifiable credentialAs constrained at issuanceAs issuedBounded by mandateYes, at issuanceAP2 / FIDO
Authorisation artifactA one-time signed approvalOne approved actionSingle use, shortOne replay attempt, if not claimedDecision, not credentialmnd8t
Funded stablecoin walletA keyAnything payable on-chainUntil drainedThe balanceNox402 for settlement

Scroll the table sideways for the remaining columns.

Reading it

Reading down the 'loss if leaked' column gives you the honest ranking, and it is roughly the order of the table. Reading down 'carries policy' shows the cost of that safety: the tightest-scoped credentials carry the least information about why the spend was permitted.

The last row is the one most often deployed by teams moving fast, and the one whose loss column should give the most pause.

Policy engines

If something evaluates the rules, what should you require of it?

Whether policy is evaluated by a network, a spend-management platform, an in-house service or a dedicated engine, the properties that make the result defensible are the same. This table is a specification to hold any candidate to, including us.

Why it matters
DeterministicSame proposal, same policy version, same answer — always. Without it, no decision can be tested before deployment or replayed afterwards.
No model in the decision pathA probabilistic decision cannot be reproduced in front of an auditor a year later. Use a model to draft policy, never to enforce it.
Versioned and immutableThe decision must name the exact policy version, and that version must not be editable afterwards, or 'what authorised this?' has no answer.
Rule-by-rule traceA score is not an explanation. The output should name which rules passed, which failed, and in what order they were evaluated.
Three outcomes, not twoAllow and deny alone force a choice between a useless agent and an unsafe one. Escalation is what lets the policy stay tight.
Stateful budgetCumulative spend, velocity and counterparty history are where the real limits live. An engine that only sees one transaction cannot enforce them.
Shadow modeYou cannot responsibly deploy a blocking control without first measuring what it would have blocked on real traffic.
Independently verifiable outputA decision that can only be verified by asking the system that made it is a log entry, not evidence.
Outside the money pathAn engine that never holds funds or credentials cannot move money if it is compromised, and is not performing a regulated payment service.
Reading it

Two of these are frequently traded away and should not be. Determinism goes first, because putting a model in the loop makes the demo better and the audit impossible. Versioning goes second, because it is invisible until the first time someone asks what the policy said in March.

Delegated authority models

Where does the authority live, and what happens when it needs to be withdrawn?

Four structurally different answers to the same question. They differ most in what happens under stress: when the agent misbehaves, when the network is unavailable, when authority must be revoked mid-flight, and when someone has to prove afterwards what was permitted.

ApproachAuthority lives inEvaluated byRevocationWorks offline from the issuerEvidence producedExpressiveness
Credential-embedded (agentic token)The tokenThe network, at authorisationDeactivate the tokenNo — the network must be in the pathAuthorisation recordsBounded by token format
Credential-carried (AP2 mandate)A signed credential the agent presentsThe relying partyUnder-specified; short lifetimes in practiceYes — signatures verify offlineSigned mandates, both stagesConstraints fixed at issuance
Policy-evaluated (engine)A versioned mandate held by the delegatorThe engine, before executionPublish a new version; effect is immediateN/A — the engine is the issuerSigned decision receipts with reasonsAnything computable, including state
Instrument-scoped (virtual card)The card's own limitsThe issuer, at authorisationCancel the cardNoCard statementsAmount, merchant, category

Scroll the table sideways for the remaining columns.

Reading it

Revocation is the column to read first, because it is the one everybody discovers late. Cancelling a card and deactivating a token are immediate and coarse. Republishing a policy is immediate and precise — and only binds the agents that ask. Revoking a credential already in an agent's hands is the genuinely unsolved case, which is why most credential designs lean on short lifetimes instead.

The offline column explains why credential-carried designs keep being proposed despite that weakness: they are the only ones that let a relying party check authority without a live call to the party that granted it.

Where mnd8t sits in these tables

In the first table mnd8t is the “policy engine (pre-transaction)” row: it can express purpose, stateful budget and counterparty history, and it is bypassable by an agent that never calls it — which is why we tell customers to keep an instrument-level cap underneath. In the second it is the authorisation artifact: not a payment credential at all, but a one-time signed approval an executor redeems. In the third it is the specification we hold ourselves to, and the limitations page says where we do not yet meet it. In the fourth it is the policy-evaluated row.

The honest summary: mnd8t does not replace a network token, a virtual card or a commerce protocol. It replaces the part of the design that is currently a spreadsheet, a code review and a hope that the agent behaves.

Last reviewed 8 September 2026. Corrections: hello@mnd8t.com.