How to add spend controls to a CrewAI flow

1. Why this guide matters

CrewAI makes it easy to coordinate agents around tasks and role boundaries. It does not itself answer whether a paid task should be allowed to run.

This guide inserts NORNR right before the paid task so the crew keeps its orchestration model while the budget and approval logic stays separate.

2. Install what you need

pip install agentpay crewai

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="crew-researcher",
    daily_limit=50,
    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

from crewai import Agent, Task, Crew

decision = wallet.pay(amount=14.00, to="openai", purpose="CrewAI task execution")

if decision.get("status") == "approved":
    researcher = Agent(role="Researcher", goal="Summarize findings")
    task = Task(description="Research the market update", agent=researcher)
    crew = Crew(agents=[researcher], tasks=[task])
    print(crew.kickoff())
else:
    print("Crew task held by policy.", 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