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

# Agentic Prompt Chaining

> Chain agents so each step's output feeds the next

Run agents in sequence — each step receives the previous step's output.

```python theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}}
from praisonaiagents import Agent, AgentFlow

researcher = Agent(name="Researcher", instructions="Research the topic. Return facts only.")
writer = Agent(name="Writer", instructions="Turn the research into a clear summary.")

flow = AgentFlow(steps=[researcher, writer])
result = flow.start("Benefits of renewable energy")
print(result["output"])
```

The user submits one goal; each agent step passes its output to the next.

```mermaid theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}}
graph LR
    In["Input"] --> S1["Step 1"]
    S1 --> S2["Step 2"]
    S2 --> S3["Step 3"]
    S3 --> Out["Output"]

    classDef agent fill:#8B0000,stroke:#7C90A0,color:#fff
    classDef step fill:#189AB4,stroke:#7C90A0,color:#fff
    classDef output fill:#10B981,stroke:#7C90A0,color:#fff

    class In,Out output
    class S1,S2,S3 step
```

## Quick Start

<Steps>
  <Step title="Simple Usage">
    Chain two agents with `AgentFlow`:

    ```python theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}}
    from praisonaiagents import Agent, AgentFlow

    researcher = Agent(name="Researcher", instructions="Research the topic.")
    writer = Agent(name="Writer", instructions="Write a summary from the research.")

    flow = AgentFlow(steps=[researcher, writer])
    result = flow.start("Benefits of renewable energy")
    ```
  </Step>

  <Step title="With Configuration">
    Add branching with `route` and step hooks:

    ```python theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}}
    from praisonaiagents import Agent, AgentFlow, route, Task

    classifier = Agent(name="Classifier", instructions="Classify the request as success or failure.")

    flow = AgentFlow(
        steps=[
            classifier,
            route({
                "success": [Agent(name="Process", instructions="Process the request.")],
                "failure": [Agent(name="Fallback", instructions="Handle the error.")],
            }),
        ],
    )
    ```
  </Step>
</Steps>

***

## How It Works

```mermaid theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}}
sequenceDiagram
    participant User
    participant Flow as AgentFlow
    participant Researcher
    participant Writer

    User->>Flow: flow.start("goal")
    Flow->>Researcher: goal
    Researcher-->>Flow: research output
    Flow->>Writer: research output as input
    Writer-->>Flow: summary
    Flow-->>User: result["output"]
```

`AgentFlow` runs steps in order. Each agent's reply becomes the next step's input. Use `route()` for conditional paths, `Task(should_run=...)` to skip steps, or `StepResult(stop_workflow=True)` to exit early.

| Pattern           | Use when                                 |
| ----------------- | ---------------------------------------- |
| Sequential agents | Fixed pipeline (research → write → edit) |
| `route()`         | Branch on classifier output              |
| `should_run`      | Skip steps based on context              |

***

## Configuration Options

| Option    | Type                  | Default        | Description                                |
| --------- | --------------------- | -------------- | ------------------------------------------ |
| `steps`   | `list`                | `[]`           | Agents, `Task`, or handler functions       |
| `process` | `str`                 | `"sequential"` | `"sequential"` or `"hierarchical"`         |
| `output`  | `OutputConfig`        | `None`         | Verbose, stream, and trace settings        |
| `hooks`   | `WorkflowHooksConfig` | `None`         | `on_step_complete` and lifecycle callbacks |
| `memory`  | `MemoryConfig`        | `None`         | Shared memory across steps                 |

***

## Best Practices

<AccordionGroup>
  <Accordion title="Keep each step focused">
    One role per agent — research, analyse, write, edit. Narrow instructions produce cleaner hand-offs.
  </Accordion>

  <Accordion title="Use route for decisions">
    Put a classifier step before `route()` rather than asking one agent to do everything.
  </Accordion>

  <Accordion title="Enable hooks for visibility">
    `WorkflowHooksConfig(on_step_complete=...)` logs progress without changing agent logic.
  </Accordion>

  <Accordion title="Start with two steps">
    Prove the pipeline with two agents, then add steps once data flow is clear.
  </Accordion>
</AccordionGroup>

***

## Related

<CardGroup cols={2}>
  <Card title="AgentFlow" icon="diagram-project" href="/docs/features/agentflow">
    Full workflow API and step types
  </Card>

  <Card title="Workflow Patterns" icon="sitemap" href="/docs/features/workflow-patterns">
    Parallel, loop, and conditional patterns
  </Card>
</CardGroup>