How to attach receipts and evidence to agent-triggered actions

1. Why this guide matters

A good control layer should not stop at the decision. You also want the artifact trail that explains what happened afterward.

This guide shows the simplest pattern for storing the decision and downstream evidence together.

2. Install what you need

pip install agentpay

This guide uses the hosted NORNR path at https://nornr.com, so you can validate the decision flow without standing up the full local stack first.

3. Create the governed wallet

from agentpay import Wallet

wallet = Wallet.create(
    owner="evidence-agent",
    daily_limit=60,
    require_approval_above=20,
    base_url="https://nornr.com",
)

This wallet is the mandate. It sets the budget and review threshold before the framework-specific workflow is allowed to continue.

4. Apply it in the workflow

decision = wallet.pay(
    amount=12.00,
    to="openai",
    purpose="agent-triggered action",
)

evidence_record = {
    "decision": decision,
    "artifact_url": artifact_url,
    "receipt_id": receipt_id,
}

store_evidence(evidence_record)

The key pattern stays the same across frameworks: ask NORNR for a decision first, then let the expensive or externally billable step run only if policy says yes.

5. What to expect

• approved means the workflow can continue immediately inside its mandate.
• queued means the request crossed an approval threshold and should wait for review.
• rejected means policy did not allow the action to proceed.

That three-way split is what makes the pattern useful: low-risk work stays fast, higher-risk work becomes reviewable, and clearly out-of-policy work never leaves the workflow.

6. Where to go next

• Hosted quickstart
• Control room
• Guides library