The cryptographic receipt of an AI action

A cryptographic receipt of an action of an agent built on artificial intelligence (AI) is a record that the checking layer creates at the moment it decides on the action: what the agent wanted to do, which rule it was checked against and what the result was. Receipts are linked into a chain by SHA-256 hashes (SHA stands for Secure Hash Algorithm), and the tip of the chain is regularly fixed with an external witness.

So an outsider (an auditor, a court, an insurer) can recompute the chain and replay the decisions on their own computer, trusting neither the owner of the agent nor the developer of the checking layer. An ordinary log cannot do this, because its administrator can quietly rewrite it.

The receipt is written before the action executes, not after, and it records a decision against a rule, allow or block. Both allows and blocks are recorded, because otherwise after an accident there is no way to tell why a destructive call went through. Each receipt contains the hash of the previous one, so changing one character in an old record breaks all later ones, and once a day the hash of the tip of the chain is fixed in the public OpenTimestamps calendars, with one hash going out and no data. An outsider recomputes the chain, matches the anchors and replays the decisions with their own instance of the solver, without taking anyone’s word for it.

How a receipt differs from a log line

A log line records that an event happened. A receipt records that an action was checked against a specific rule and what the answer was, and it links this record to its neighbors so that it cannot be quietly changed.

Log lineCryptographic receipt
When it is writtenAfter the actionAt the moment of decision, before execution
What it recordsThe fact of an eventThe request, the rule (by fingerprint), the check’s answer, the outcome
Who can correct itThe server administrator, and the agent itself if it has the rightsNo one, quietly: a change breaks the chain and diverges from the anchor
Who checks itWhoever is trusted on their wordAny outsider on their own machine
Evidential weightDepends on trust in the ownerFollows from recomputation

What a receipt records

In the architecture described in the book of the institute “Proven Action” (Chapter 10), a decision receipt has four groups of fields.

  1. Whose action and what kind: the tenant, the channel and the class of action, for example sending data out, deletion, a push to a repository, stopping a service.
  2. Observed facts and the rule: the values the classifier saw and the server established, and the rule: its class, revision number and the SHA-256 fingerprint of its text. There is no human signature in the receipt: the rule’s revision is fixed by the fingerprint, and the rule’s text is stored next to the chain once per revision.
  3. The decision: whether the action is admissible, the solver’s answer, the grounds for admission or the repair conditions, the mode (advice, block), the final verdict and the decision time.
  4. The link to the chain: the hash of the previous receipt and the hash of this one.

Why receipts are linked into a chain

The chain prevents a record from being deleted, inserted or reordered. The hash of each receipt is computed from the hash of the previous one and its own body: Hₙ = SHA-256(Hₙ₋₁ ∥ Pₙ). If even one character changes in receipt k, its hash changes, and with it the hashes of all later ones, so recomputing the chain shows where it breaks.

A chain has a limit: whoever controls the whole disk can rewrite receipt k and recompute all hashes after it, and the chain stays internally consistent. That is why an external witness is needed.

The external witness: OpenTimestamps

Once a day the hash of the chain’s tip (one 64-character string) is fixed in the public calendars of the OpenTimestamps protocol. The calendars aggregate fingerprints into a Bitcoin transaction and return a proof of existence. After that, the chain up to the fixed tip cannot be rewritten unnoticed: a new chain will not match the anchor, which is kept outside the owner’s control.

The contents of the receipts cannot be recovered from one tip hash, so no requests, file names, amounts or personal data go out. In a closed perimeter without network access the public calendar is unreachable, and the tip hash has to be carried by hand to a node with network access or fixed with a timestamping service that the customer appoints. Until it is fixed, the records are protected only by the chain, and the procedure for fixing is set during deployment.

How to check receipts without trusting the owner

The checker receives the chain of receipts, the rule texts and the verifier, and takes the anchors with their timestamps from the open verification kit. Then the checker takes three steps on their own machine, with no connection to the checked server.

  1. Recompute the chain: the hashes of all receipts match, so no records were deleted, inserted or changed.
  2. Match the anchors: the chain’s tips match the fingerprints fixed in OpenTimestamps on their dates.
  3. Replay the decisions: for each receipt, give the rule text and the observed facts to their own instance of the solver and get the same answer.

The open part of the verification kit (chain anchors, their OpenTimestamps proofs and the integrity verifier) is published at asi5.ru/console/verify/. In the historical epoch-33 anchor on 25 October 2026 the chain held 5,094 records and the verifier replayed 5,079 decisions out of 5,079 (on 14 October 2026, 4,958 out of 4,958). As of 15 November 2026, the live receipt chain holds 5,373 records across 55 completed epochs (56 published). For regulated Russian banks and critical information infrastructure, OpenTimestamps proofs are paired with accredited trust service time stamps and qualified electronic signatures under Federal Law No. 63-FZ. This replay was run by the institute itself, and an independent checker has not yet done it. The procedure is on the page of the independent verification protocol.

What a receipt proves, and what it does not

ProvesDoes not prove
The action was checked against the rule of this revision, and the check gave this answerThat the rule itself was good: a bad rule will honestly let a bad action through
Records up to the fixed anchor were not deleted or changedThe integrity of records after the latest anchor: only the chain protects them until the next fixing
The decisions can be replayed by an outsiderCompliance with a regulator’s requirements: the organization and the certification body establish that

A receipt turns an argument from trust in a word into a recomputation. Responsibility for the rules still lies with the person who approved them.

Who needs a receipt and why

Frequently asked questions

What is a cryptographic receipt of an AI action?

A record of a decision on an AI agent’s action: what it wanted to do, which rule it was checked against and with what result. Receipts are linked into a chain by SHA-256 hashes, and the chain’s tip is fixed with an external witness, so the record cannot be quietly changed and an outsider can check it.

How does a receipt differ from an ordinary log?

A log is written after the event and kept by the owner, who can correct it. A receipt is written at the moment of decision, records the rule and the answer of the check, and is linked to neighboring records so that any change is found by recomputation.

Why record allowed actions, not only blocks?

To understand after an accident why a destructive action went through: a gap in a rule, a soft “advice” mode or a classifier error. If only blocks are kept, there is nothing to answer that question with.

How can a chain of receipts be checked without trusting the owner?

The checker recomputes the hashes of all receipts, matches the tips of the chain against the OpenTimestamps anchors and replays the decisions with their own instance of the solver using the rule texts. All of this runs on the machine of the checker, with no connection to the checked server.

Does company data leave the perimeter when fixed with the external witness?

No. Only the hash of the chain’s tip goes out: 64 characters from which the receipts’ contents cannot be recovered; requests, file names, amounts and personal data stay inside the perimeter.

Does a receipt prove that the agent acted correctly?

It proves that the action was checked against a rule of a certain revision and that the record was not changed. Whether the rule itself is good, the receipt does not prove: the person who approved the rules answers for them.

Sources

  1. The institute’s book “Proven Action. Power and Control over AI Agents: Strategy 2027–2035”, Chapter 10 (in Russian): https://isslab.ai/book/
  2. Independent verification protocol: https://isslab.ai/book/verification-protocol/
  3. Open chain verification kit: https://asi5.ru/console/verify/
  4. OpenTimestamps: https://opentimestamps.org/
  5. National Institute of Standards and Technology (NIST), Federal Information Processing Standard (FIPS) 180-4, Secure Hash Standard: https://csrc.nist.gov/pubs/fips/180-4/upd1/final

Checked: 18 October 2026, against the text of the book and the published verification kit.