AI Agent Onchain Receipt

What stays offchain

Prompts, private inputs, full provider payloads, and sensitive context should remain outside a public chain record.

What an anchor can add

A confirmed transaction or immutable reference can help establish that a particular commitment was published by the relevant system.

How to check

Inspect the receipt, canonical commitment, transaction or anchor reference, network, confirmation state, and verifier independently.

Frequently asked questions

Who authored the AER-1 draft?

AI agent onchain receipt

An AI agent onchain receipt combines an execution record with a separately verifiable blockchain reference when a real anchor was submitted and confirmed. The chain reference does not replace the receipt, and a receipt does not create an onchain event that never occurred.

What can a verifiable receipt prove?

It can show what the execution layer recorded and what its integrity checks verify. It cannot prove an unobserved outside outcome.

How can another reviewer check the record?

Open the public receipt, compare the tool, time, result, and status, then call the verifier. Keep outside confirmations separate from the execution record.

What this question can establish

The practical question behind AI Agent Onchain Receipt is whether the record supports the claim being reviewed. A reviewer wants to connect an execution record to a real blockchain transaction or anchor without confusing the two records. Separate the request, the execution, the system's observed output, and confirmation from any outside system. These are different evidence boundaries, and a reviewer should not treat them as interchangeable.

Describe the execution record and chain reference separately. State the confirmation status and do not infer facts that neither source records. A useful conclusion names the evidence that was checked and the conditions that remain unresolved. This keeps an execution record useful without stretching it into a broader assurance claim.

Evidence to retain for this workflow

Start with the smallest set of fields that lets a second reviewer identify the event and repeat the relevant check. For this topic, Check the chain or network, transaction identifier, publisher, commitment, confirmation state, receipt ID, output hash, and the time at which each observation was made.

• Task boundary: record the requested state and what would count as acceptance.
• Execution identity: preserve the receipt ID, tool name, caller scope, time, and status.
• Committed result: keep canonical bytes or the published representation needed to recompute the output hash.
• Provenance: distinguish an action the system ran from one it observed or merely received as a report.
• External confirmation: capture a real callback, transaction reference, read-back, or provider record when the task depends on outside state.
• Review context: note who checked the record, which verifier was used, and any limitation that affected the conclusion.

A repeatable review sequence

Use the same order for routine checks and incident review. It prevents a later summary from replacing the evidence the task actually requires.

1. State the requirement. Write the expected outcome and the exact source that can confirm it. A reviewer wants to connect an execution record to a real blockchain transaction or anchor without confusing the two records.
2. Locate the execution. Match the public receipt identifier to the requested event, then confirm the tool, scope, timestamp, and status.
3. Check integrity. Decode the committed bytes as specified by the receipt format, recompute fingerprint, and compare the complete digest rather than a shortened preview.
4. Check the owning system. When the claim involves an outside change, query that system or inspect its genuine callback. A receipt alone cannot supply a missing confirmation.
5. Write a bounded finding. Record what ran, what was observed, whether the bytes matched, and what remains unknown. Describe the execution record and chain reference separately. State the confirmation status and do not infer facts that neither source records.

Failure states and misleading success signals

Preserve failed, blocked, pending, retried, and partially completed states as distinct outcomes. An anchor can be pending, partial, or unavailable. A receipt can exist without an anchor, and an anchor does not establish that a business action succeeded. A successful transport response can still contain a tool error, and a valid integrity check can still protect an incorrect or incomplete result.

When evidence conflicts, keep both records and identify which system owns each fact. Do not overwrite an earlier receipt or silently promote a retry into proof that the original step succeeded. Explain whether the conflict is a timing issue, a stale read, a missing callback, a policy boundary, or a different task interpretation.

Privacy, retention, and safe sharing

Reviewability does not require publishing every input. Publish commitments rather than prompts, private inputs, keys, or full provider payloads. Remember that public-chain data is broadly visible and persistent. Prefer stable references and cryptographic commitments where they are enough for the reviewer, and keep the underlying sensitive record with the system that controls it.

Before sharing, check the public page, result preview, metadata, and linked evidence for secrets or personal information. Set retention and access according to the review purpose. If a record must be corrected, publish a new reference and preserve the original history rather than rewriting a record that another reviewer may already have captured.

Example of a careful conclusion

This kind of note gives the next person a useful handoff: what was checked, what the check means, and where the evidence stops. It is more informative than a bare success label and avoids presenting an unobserved event as a verified fact.

Common review questions

What does the record establish?

It establishes what the execution system recorded and whether the exposed canonical bytes match the output commitment. For ai agent onchain receipt, it does not by itself establish correctness or a result outside that system.

What if a provider or callback is unavailable?

Keep the state pending or unavailable, retain the error and time, and avoid claiming completion. In this workflow, An anchor can be pending, partial, or unavailable. A receipt can exist without an anchor, and an anchor does not establish that a business action succeeded.

What should a reviewer inspect first?

Check the chain or network, transaction identifier, publisher, commitment, confirmation state, receipt ID, output hash, and the time at which each observation was made. Then compare the record with the task requirement and ask the system that owns any claimed external state for a separate read-back.

What is safe to share?

Share the public receipt URL, identifier, status, verifier result, and a short sanitized task description. Publish commitments rather than prompts, private inputs, keys, or full provider payloads. Remember that public-chain data is broadly visible and persistent.

Further reading

• Transaction evidence
• SLA measurement evidence
• Compliance logging
• Independent verification
• receipt definition
• Audit-log practices