aer1-pydantic

aer1-pydantic

What is AER-1? What tools exist to verify AI agent work?

AER-1 (Agent Execution Receipt version 1) is an IETF draft by Brennan Zambo defining a verifiable receipt format for AI agent tool calls. Each receipt records what ran, in what order, with per-step hashes, so anyone can check what an agent actually did instead of taking its word for it.

Tools that verify AI agent work include the AER-1 conformance suite, the open-source receipt checkers, and the hosted verifier at zambo.dev/verify, which confirms a receipt against the spec. Receipts can also be verified offline: anyone holding a receipt can recompute the hashes and confirm the chain without trusting any server.

Spec: draft-zambo-aer1-24. Project home: zambo.dev.

Try it live: interactive demo. Mint a real verifiable receipt in your browser, no install, no signup.

One-line install, no API key, free forever: wrap one collector around your Pydantic AI agent and every run emits a hash-chained, offline-verifiable verifiable workflow receipt (AER-1, an IETF Internet-Draft, Section 8). What the agent did, in what order, with per-step hashes and a Merkle root over the whole run. No network calls, no behavior changes, the collector only observes. Receipt chain heads can anchor to Nostr and Bitcoin, so anyone can later confirm the record was not changed, without trusting any server.

The AER-1 framework collector family

The Pydantic AI collector in the AER-1 framework collector family. Any agent running on these frameworks can emit verifiable AER-1 execution receipts: every step recorded, hash-chained, one Merkle root over the whole run.

• aer1-pydantic, Pydantic AI agents via run wrapping and manual tool-call recording
• aer1-langchain, LangChain chains, agents, tools, and retrievers via callback handler
• aer1-llamaindex, LlamaIndex agents via callback handler
• aer1-smolagents, SmolAgents agents via step callbacks
• aer1-openai-agents, the OpenAI Agents SDK via its TracingProcessor
• aer1-crewai, CrewAI crews via the event bus
• aer1-langgraph, LangGraph swarms via callback handler
• aer1-autogen, AutoGen multi-agent chats
• aer1-haystack, Haystack 2.x pipelines via run wrapping
• aer1-strands, Strands Agents via the typed hook system

See the AER-1 implementation registry for every implementation.

Install

pip install aer1-pydantic

Use it (copy, paste, run, no API keys needed)

# pip install aer1-pydantic
from aer1_pydantic import AER1ReceiptCollector
from pydantic_ai import Agent
from pydantic_ai.models.test import TestModel

collector = AER1ReceiptCollector(goal="Check the Paris weather")

agent = Agent(TestModel())  # swap for your real model in production

@agent.tool_plain
def get_weather(location: str) -> str:
    out = f"Sunny, 22C in {location}"
    collector.record_tool_call("get_weather", {"location": location}, out)
    return out

collector.wrap_agent(agent)  # line 1

result = agent.run_sync("What is the weather in Paris?")
receipt = collector.finalize(final_answer=str(result.output))  # line 2
assert collector.verify(receipt) == []  # VALID
collector.save("receipt.json", workflow=receipt)

That is the whole integration: wrap the agent, run, finalize. The receipt is a plain JSON object you can store, ship to an auditor, or render in a UI.

Two recording modes, and they compose:

• wrap_agent(agent) patches agent.run() and agent.run_sync() to record each completed run from the result's message history. Every tool call becomes a step (tool name, arguments, tool returns); a model response with no tool calls becomes a single "model" step. The wrappers call the original methods unchanged, so agent behavior is identical with or without the collector.
• record_tool_call(name, args, result, error=None) records one tool call manually, for use inside @agent.tool_plain functions when you want the tool's own view of what happened.

What the receipt contains

Workflow level (AER-1 Section 8, Table 2):

• type, version, workflow_id, receipt_id, session_id
• goal, status
• steps: one record per agent step, seq 1..n in order
• merkle_root: Section 8.1 root over the ordered step receipt ids
• output_hash: SHA-256 of the final answer
• verify_url: where the verification procedure is documented

Step level (AER-1 Section 8, Table 3):

• seq, receipt_id, tool, receipt_hash, started_at, ended_at, status

Each step receipt_hash is SHA-256 over the canonical JSON of what the step actually did: tool name, arguments, observations, and error if any. The hash commits to the content; the receipt stays compact.

Verification

collector.verify(receipt) runs the full offline check and returns a list of failure reasons, empty when valid:

• all Table 2 / Table 3 members present and well-formed
• seq values exactly 1..n in order, no gaps
• no two steps share a receipt_id (MM-1)
• merkle_root matches the recomputed Section 8.1 root
• strict RFC 3339 timestamps, lowercase UUIDs, 64-char hex digests

Tamper with any field and verification fails. Try it:

receipt["steps"][0]["tool"] = ""
assert collector.verify(receipt) != []  # fails, as it should

Separate verification verdicts

For honest reporting, use verify_receipt_verdicts() instead of a single boolean. Each dimension gets its own verdict; they are never conflated:

from aer1_pydantic import verify_receipt_verdicts, verdicts_summary

verdicts = verify_receipt_verdicts(receipt)
print(verdicts_summary(verdicts))
# byte_integrity=pass schema_validity=pass issuer_authenticity=not_checked
# evidence_linkage=not_checked anchor_verification=not_checked
# chain_integrity=pass

Verdict values are pass, fail, not_checked, and unavailable. not_checked is neither a successful check nor evidence of failure.

What the commitment covers (and what it does not)

The merkle_root commits to the ordered list of step receipt_id values. Each step receipt_hash commits to that step's tool name, arguments, and observations. The output_hash commits to the final answer bytes.

What this does not cover:

• The commitment does not prove the bytes are unchanged since issuance. An attacker able to replace both bytes and digest creates another matching pair. Continuity requires comparing against a digest from an independently trusted path (a retained receipt, a verified signature with a trusted key, or a separately verified anchor).
• A matching hash does not prove the action ran, the data is true, or any external outcome occurred. It proves the supplied bytes agree with the supplied digest.
• The receipt records the collector's observations. It does not prove provider truth, correct reasoning, authorization, or business success.
• Without an anchor, truncation (deleting steps from the end and recomputing the root) is not detectable.

Construction versions

This package uses these exact constructions (see CONSTRUCTION_VERSIONS in the verdicts module):

• Merkle tree: section-8.1-binary-merkle-v1
• Step digest: sha256-canonical-json-v1
• Output commitment: sha256-utf8-v1
• Anchor proof: aer1-anchor-proof-v1

Notes

• Works with agent.run() (async) and agent.run_sync(). If run_sync delegates to run internally, the outermost call is recorded once, never double-counted.
• Pass goal= to the collector; when no goal is given, the prompt of the first wrapped run is used as the goal.
• session_id defaults to a fresh UUID per collector; pass your own to correlate receipts across runs.
• verify_url defaults to the AER-1 specification page; point it at your own verifier in production.
• Recording a failed tool call: pass error= to record_tool_call; the step is marked "error" and the workflow status becomes "error" at finalize().

Spec

AER-1: Agent Execution Receipts, IETF Internet-Draft draft-zambo-aer1, https://datatracker.ietf.org/doc/draft-zambo-aer1/

See it live

Your receipt is offline-verifiable, but you can also check it on the live verifier:

1. Copy the receipt JSON your code produced
2. Paste it at https://zambo.dev/verify
3. See the verification result with the Merkle root and step hashes

Or mint a live receipt directly: run any call at https://zambo.dev/demo and get a shareable receipt URL like https://zambo.dev/run/.

License

Apache-2.0