> ## 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.
# Workflows
> Understanding workflow patterns for multi-agent systems
Pick a workflow pattern and connect agents so they share context across steps.
```python theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}}
from praisonaiagents import Agent, AgentFlow
researcher = Agent(name="Researcher", instructions="Research topics.")
writer = Agent(name="Writer", instructions="Write clear summaries.")
flow = AgentFlow(steps=[researcher, writer])
flow.start("Explain workflow patterns in one paragraph.")
```
The user chooses a pattern, configures agents, and submits a task that flows through the team.
```mermaid theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}}
graph LR
subgraph "Workflows"
U[📋 Task] --> A[🤖 Agent Team]
A --> O[✅ Result]
end
classDef input fill:#6366F1,stroke:#7C90A0,color:#fff
classDef process fill:#189AB4,stroke:#7C90A0,color:#fff
classDef output fill:#10B981,stroke:#7C90A0,color:#fff
class U input
class A process
class O output
```
## Quick Start
Chain two agents so the second builds on the first.
```python theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}}
from praisonaiagents import Agent, AgentFlow
researcher = Agent(name="Researcher", instructions="Research topics.")
writer = Agent(name="Writer", instructions="Write clear summaries.")
flow = AgentFlow(steps=[researcher, writer])
flow.start("Explain workflow patterns in one paragraph.")
```
Run independent agents together with the top-level `parallel` primitive.
```python theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}}
from praisonaiagents import Agent, AgentFlow, parallel
ai = Agent(name="AI", instructions="Research AI trends")
ml = Agent(name="ML", instructions="Research ML trends")
summary = Agent(name="Summary", instructions="Combine research")
flow = AgentFlow(steps=[parallel([ai, ml]), summary])
flow.start("Research latest developments")
```
***
## How It Works
```mermaid theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}}
sequenceDiagram
participant User
participant AgentFlow
participant Agent
User->>AgentFlow: start("task")
AgentFlow->>Agent: Run each step in order
Agent-->>AgentFlow: Step output feeds the next
AgentFlow-->>User: Final result
```
***
# Workflows
Workflows define **how multiple agents work together** to complete a task. Just like a team of people in an office, agents can collaborate in different ways depending on the task.
## What is a Workflow?
Think of a workflow as a **recipe** that tells your agents:
* Who does what
* In what order
* How they share information
```mermaid theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}}
graph LR
subgraph "Workflow = Recipe for Agents"
A["📋 Task"] --> B["🤖 Agent 1"]
B --> C["🤖 Agent 2"]
C --> D["✅ Result"]
end
classDef task fill:#8B0000,stroke:#7C90A0,color:#fff
classDef agent fill:#189AB4,stroke:#7C90A0,color:#fff
classDef result fill:#10B981,stroke:#7C90A0,color:#fff
class A task
class B,C agent
class D result
```
## The Four Main Patterns
**"Send to the right expert"**
Like a receptionist directing calls to the right department.
**"Everyone works at once"**
Like a team researching different topics simultaneously.
**"One step at a time"**
Like passing a document from person to person for review.
**"Manager delegates work"**
Like a project manager assigning tasks to team members.
***
## Which Pattern Should I Use?
| I want to... | Use this pattern |
| --------------------------------------- | ---------------- |
| Send requests to different specialists | **Routing** |
| Do multiple independent things at once | **Parallel** |
| Process step-by-step (A → B → C) | **Sequential** |
| Let an AI decide how to break down work | **Orchestrator** |
***
## Real-World Examples
### Example 1: Customer Support Bot
A customer asks: *"Why is my order delayed?"*
| Pattern | How it works |
| -------------- | ---------------------------------------------- |
| **Routing** | Classify the question → Send to Shipping Agent |
| **Sequential** | Lookup Order → Check Status → Write Response |
### Example 2: Research Report
You ask: *"Create a report on AI trends"*
| Pattern | How it works |
| ---------------- | ------------------------------------------------------- |
| **Parallel** | Research AI + Research ML + Research NLP (all at once) |
| **Sequential** | Research → Analyze → Write → Edit (step by step) |
| **Orchestrator** | Manager assigns: "You research, you analyze, you write" |
***
## Two Ways to Build Workflows
PraisonAI offers two approaches:
| Approach | Class | Best for |
| --------------------------- | ---------------------------- | ------------------------------- |
| **Deterministic Pipelines** | `AgentFlow` | You define exactly what happens |
| **Dynamic Delegation** | `AgentTeam` + `hierarchical` | AI manager decides |
**Start simple**: Use Sequential for your first workflow, then explore other patterns as needed.
***
## Best Practices
Independent subtasks fit `parallel`; ordered steps fit sequential; expert routing fits routing. Choosing the shape first keeps flows simple.
`AgentFlow(steps=[...])` runs exactly the steps you list. Reach for `AgentTeam` + hierarchical only when you want an AI manager to decide.
`from praisonaiagents import parallel` (and `when`, `loop`) uses the friendly re-exports, so samples stay short and portable.
***
## Next Steps
Start with the simplest pattern
Technical API documentation