How to Generate Cryptographic Proof of AI Agent Authorization (EU AI Act Article 14)

EU AI Act Article 14 enforcement starts August 2, 2026. If you're building AI agents that access sensitive data, process customer information, or make autonomous decisions — you need to demonstrate human oversight with verifiable artifacts.

Not logs. Not observability traces. Cryptographic proof.

In this post, I'll show you how we built Verigate — a cryptographic trust infrastructure for AI agents — and how you can use it to generate tamper-evident authorization receipts that any auditor can verify offline.

This content was created for the Build with Gemini XPRIZE.

Every AI agent platform today — LangChain, CrewAI, Google ADK, Zapier AI — lets agents take actions. But none of them produce independently verifiable proof that the action was authorized according to policy.

When your agent:

...what evidence exists that this action was authorized? A database log? That can be modified. An observability trace? That's vendor-dependent. A timestamp? That proves when, not whether.

Article 14 of the EU AI Act requires deployers to demonstrate five capabilities:

That fifth requirement is where most teams fail. You need artifacts that are:

Here's how Verigate solves this:

When an agent requests authorization, the gateway evaluates policy rules (allowlist, resource scope, rate limit) and produces an Ed25519-signed receipt:

{
  "body": {
    "v": "1",
    "seq": "42",
    "ts": "2026-06-26T10:30:00Z",
    "request_digest": "sha256:0e6d5b86f01f...",
    "policy_version": "sha256:d59a1e4171e6...",
    "decision": "approve",
    "reasons": [],
    "prev_receipt": "sha256:b3f51c8824bc..."
  },
  "sig": {
    "alg": "EdDSA",
    "kid": "gateway-prod-a1b2c3d4",
    "value": "7WiFneT3tLRtE2Iztm..."
  },
  "receipt_hash": "sha256:2a3e65a3ade468..."
}

Key properties:

Each receipt's prev_receipt

field contains the SHA-256 hash of the previous receipt. This creates a tamper-evident chain:

Receipt #1 (genesis) → prev: sha256:0000...0000
Receipt #2 → prev: sha256(Receipt #1)
Receipt #3 → prev: sha256(Receipt #2)
...

Modify any receipt in the chain, and every subsequent prev_receipt

hash becomes invalid. Insert or delete a receipt, and the sequence numbers break.

Receipt hashes are organized into a Merkle tree using domain-separated hashing:

Leaf:  SHA256("BI_RECEIPT_LEAF_V1" || 0x00 || receipt_hash)
Node:  SHA256("BI_RECEIPT_NODE_V1" || 0x00 || left || right)

This lets you prove a specific receipt is included in a batch without down all receipts. The /v1/engine/merkle/proof

endpoint returns the sibling hashes and directions.

For regulated industries, the Merkle root can be anchored on Base mainnet (chain ID 8453) as transaction calldata:

Anchor TX → burn address (0x000...000)
Value: 0
Calldata: 32-byte Merkle root

This creates an immutable timestamp proving the receipt chain existed at a specific block height. Verifiable on BaseScan by anyone, forever.

Here's what makes this architecture unique: the authorization decision is fully deterministic. No AI model can influence whether an action is allowed or denied. The policy engine evaluates three rule types:

All three must pass. Any failure → deny.

Gemini (via Vertex AI) powers six AI agents that sit outside the authorization path:

The security boundary is explicit: AI advises, the gateway decides.

from sdk import Verigate

vg = Verigate(api_key="as_...")

vg.register_agent("my-bot", name="My Bot", capabilities=["read", "query"])

result = vg.authorize("my-bot", action="read", resource="/data/users")
print(f"Decision: {result.decision}")
print(f"Receipt: {result.receipt_hash}")

chain = vg.verify_chain()
print(f"Chain valid: {chain['valid']}")
report = vg.generate_compliance_report(
    agent_name="my-bot",
    agent_description="Reads customer profiles from staging database",
    capabilities=["read", "query"],
    data_types=["PII", "customer_records"],
    frameworks=["EU AI Act", "HIPAA", "SOC 2"],
)
print(f"Findings: {len(report.findings)}")
{
  "mcpServers": {
    "verigate": {
      "command": "python",
      "args": ["/path/to/mcp_server.py"],
      "env": { "VERIGATE_API_KEY": "as_..." }
    }
  }
}

56 tools available — authorize, verify, register agents/resources/actions, generate compliance reports, chat with the multi-agent system.

Not ready to commit? Try the free compliance quick-scan — describe your agent and get 3 EU AI Act findings in 30 seconds. No signup required.

Full report with all 6 frameworks (EU AI Act, HIPAA, SOC 2, DORA, NIST AI RMF, OWASP LLM Top 10): $299 one-time.

Built with Google Gemini 2.5 (Vertex AI), Google ADK 2.1, Cloud Run, and Firestore.