> ## 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: Agent Decorator

> Attach budget, compliance, and KPI policies directly to agent functions with @cascadeflow.agent().

# Agent Decorator — Policy Per Agent

The `@cascadeflow.agent()` decorator attaches policy metadata directly to agent functions. Each agent gets its own budget, compliance rules, and KPI weights — enforced automatically at runtime.

## Basic Usage

```python theme={null}
import cascadeflow

cascadeflow.init(mode="enforce")

@cascadeflow.agent(budget=0.20)
async def my_agent(query: str):
    """This agent cannot spend more than $0.20."""
    return await llm.complete(query)
```

## Add Compliance

```python theme={null}
@cascadeflow.agent(budget=0.50, compliance="gdpr")
async def eu_agent(query: str):
    """Process EU data — only GDPR-approved models, $0.50 max."""
    return await llm.complete(query)
```

## Add KPI Weights

Encode business priorities into how the agent makes model decisions:

```python theme={null}
@cascadeflow.agent(
    budget=1.00,
    kpi_weights={"quality": 0.8, "cost": 0.2},
    kpi_targets={"quality": 0.9},
)
async def premium_agent(query: str):
    """High-quality responses — prioritize quality over cost."""
    return await llm.complete(query)
```

## Different Agents, Different Policies

The real power shows with multiple agents — each governed independently:

```python theme={null}
@cascadeflow.agent(
    budget=0.10,
    kpi_weights={"cost": 0.9, "quality": 0.1},
)
async def triage_agent(query: str):
    """Quick classification — optimize for cost."""
    return await llm.complete(query)

@cascadeflow.agent(
    budget=2.00,
    compliance="hipaa",
    kpi_weights={"quality": 0.9, "cost": 0.1},
    kpi_targets={"quality": 0.95},
)
async def medical_agent(query: str):
    """Patient data — strict compliance, high quality, higher budget."""
    return await llm.complete(query)

@cascadeflow.agent(
    budget=0.50,
    max_tool_calls=5,
)
async def research_agent(query: str):
    """Research with tools — capped at 5 tool calls and $0.50."""
    return await llm.complete(query)
```

## Combine with run()

The decorator works alongside `cascadeflow.run()` — the run's constraints apply in addition to the decorator's:

```python theme={null}
@cascadeflow.agent(budget=0.50, compliance="gdpr")
async def my_agent(query: str):
    return await llm.complete(query)

# The run adds an outer budget cap on top of the agent's own cap
with cascadeflow.run(budget=2.00) as session:
    await my_agent("First query")   # Agent cap: $0.50, Run cap: $2.00
    await my_agent("Second query")  # Agent cap: $0.50, Run cap: $2.00 minus first query
    print(session.summary())
```

## All Decorator Parameters

| Parameter        | Type    | Description                                              |
| ---------------- | ------- | -------------------------------------------------------- |
| `budget`         | `float` | Max USD for this agent                                   |
| `compliance`     | `str`   | `"gdpr"`, `"hipaa"`, `"pci"`, or `"strict"`              |
| `kpi_weights`    | `dict`  | Relative weights: `quality`, `cost`, `latency`, `energy` |
| `kpi_targets`    | `dict`  | Target values per KPI dimension                          |
| `max_tool_calls` | `int`   | Max tool/function calls per invocation                   |

<Tip>
  **API reference:** [@cascadeflow.agent()](/api-reference/python/agent-decorator) | **Example:** [examples/agentic\_multi\_agent.py](https://github.com/lemony-ai/cascadeflow/blob/main/examples/agentic_multi_agent.py)
</Tip>

## Next Step

Understand how the Harness works under the hood. [Learn the Agent Harness →](/get-started/agent-harness)