> ## Documentation Index
> Fetch the complete documentation index at: https://docs.cascadeflow.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# Quickstart: Enforce Mode

> Add budget caps and constraints that actively control agent execution — stop runs, switch models, and gate tool calls.

# Enforce Mode — Active Runtime Control

Enforce mode moves from observation to action. Budget caps, tool call limits, and compliance rules become hard constraints that shape agent behavior in real time.

<Steps>
  <Step title="Switch to enforce">
    ```python theme={null}
    import cascadeflow

    cascadeflow.init(mode="enforce")  # Changed from "observe" to "enforce"
    ```
  </Step>

  <Step title="Add a budget cap">
    Wrap any block of agent work with `cascadeflow.run()` and set a budget:

    ```python theme={null}
    cascadeflow.init(mode="enforce")

    with cascadeflow.run(budget=0.50) as session:
        result = await agent.run("Research and summarize this topic")

        summary = session.summary()
        print(f"Cost: ${summary['cost_total']:.4f}")
        print(f"Budget remaining: ${summary['budget_remaining']:.4f}")
        print(f"Steps completed: {summary['steps']}")
    ```

    If the agent exceeds \$0.50, cascadeflow issues a `stop` action. The agent halts cleanly — no runaway spend.
  </Step>

  <Step title="Combine budget with tool call limits">
    ```python theme={null}
    with cascadeflow.run(budget=1.00, max_tool_calls=5) as session:
        result = await agent.run("Search and analyze this dataset")
        # Stops when either budget OR tool call limit is hit first
    ```
  </Step>

  <Step title="Add compliance gating">
    Restrict which models can process sensitive data:

    ```python theme={null}
    with cascadeflow.run(budget=1.00, compliance="gdpr") as session:
        result = await agent.run("Process EU customer feedback")
        # Only GDPR-approved models are allowed — non-compliant models are switched
    ```
  </Step>

  <Step title="See what happened">
    The decision trace shows every enforcement action:

    ```python theme={null}
    for record in session.trace():
        print(f"Step {record['step']}: {record['action']} — {record['reason']}")
        # Step 1: allow — budget ok, compliance passed
        # Step 3: switch_model — model not in GDPR allowlist
        # Step 7: stop — budget exceeded ($0.50/$0.50)
    ```

    In enforce mode, `record['applied']` is `True` — actions are executed, not just logged.
  </Step>
</Steps>

## Gradual Rollout

You do not need to jump from observe to full enforcement. Start with one constraint:

```python theme={null}
# Week 1: Just budget — see if anything would stop
cascadeflow.init(mode="enforce")
with cascadeflow.run(budget=5.00) as session:  # Generous cap
    ...

# Week 2: Add tool call limits
with cascadeflow.run(budget=2.00, max_tool_calls=20) as session:
    ...

# Week 3: Add compliance
with cascadeflow.run(budget=1.00, max_tool_calls=10, compliance="gdpr") as session:
    ...
```

## TypeScript

```typescript theme={null}
import { CascadeAgent } from '@cascadeflow/core';

const agent = new CascadeAgent({
  models: [
    { name: 'gpt-4o-mini', provider: 'openai', cost: 0.000375 },
    { name: 'gpt-4o', provider: 'openai', cost: 0.00625 },
  ],
  quality: {
    threshold: 0.8,
    useSemanticValidation: true,
  },
});

const result = await agent.run('Explain quantum computing');
console.log(`Model: ${result.modelUsed}, Saved: ${result.savingsPercentage}%`);
```

<Tip>
  **Run this example:** [examples/enforcement/basic\_enforcement.py](https://github.com/lemony-ai/cascadeflow/blob/main/examples/enforcement/basic_enforcement.py) | [examples/user\_budget\_tracking.py](https://github.com/lemony-ai/cascadeflow/blob/main/examples/user_budget_tracking.py)
</Tip>

## Next Step

Ready to attach policy to individual agents? [Use the @agent decorator →](/get-started/agent-decorator)