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.

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.

Quick Start

1. Simple Usage

   Chain two agents with AgentFlow:

   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")
   
2. With Configuration

   Add branching with route and step hooks:

   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.")],
           }),
       ],
   )
   

---

How It Works

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

Keep each step focused

One role per agent — research, analyse, write, edit. Narrow instructions produce cleaner hand-offs.

Use route for decisions

Put a classifier step before route() rather than asking one agent to do everything.

Enable hooks for visibility

WorkflowHooksConfig(on_step_complete=...) logs progress without changing agent logic.

Start with two steps

Prove the pipeline with two agents, then add steps once data flow is clear.

---

Related

AgentFlow

Full workflow API and step types

Workflow Patterns

Parallel, loop, and conditional patterns