How to add audit trail to AutoGen tool execution

1. Why this guide matters

AutoGen is powerful when multiple agents and tools collaborate. That collaboration becomes much harder to reason about once one of those tools can create cost or external commitment.

This guide uses NORNR to wrap the tool execution path so the decision object stays attached to the run.

2. Install what you need

pip install agentpay autogen-agentchat

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="autogen-operator",
    daily_limit=70,
    require_approval_above=25,
    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

from autogen_agentchat.agents import AssistantAgent

decision = wallet.pay(amount=16.00, to="openai", purpose="tool execution")

assistant = AssistantAgent(name="ops", model_client=None)

if decision.get("status") == "approved":
    print("Run the tool and persist the NORNR decision next to the result.", decision)
else:
    print("Tool execution paused or blocked.", decision)

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