Output Variables

An output_variable names a task’s result so later tasks can read it.

Available under PraisonAIAgents / AgentTeam as of PraisonAI PR #4907. Earlier releases only exposed output_variable inside the standalone Workflow engine and its YAML syntax.

Quick Start

Store one task's output

Name the result with output_variable.

from praisonaiagents import Agent, Task

researcher = Agent(name="Researcher", instructions="Research the topic and list key facts.")

research = Task(
    name="research",
    action="Research renewable energy trends",
    agent=researcher,
    output_variable="research_data",
)

Read it in the next task

Reference the stored value with {{research_data}} in a later task’s action.

from praisonaiagents import Agent, Task, PraisonAIAgents

writer = Agent(name="Writer", instructions="Write a short report.")

report = Task(
    action="Write a report using {{research_data}}",
    agent=writer,
    context=[research],
)

PraisonAIAgents(
    agents=[researcher, writer],
    tasks=[research, report],
).start()

How It Works

After any task completes — agent or handler — its raw output is stored under the given name in the team’s shared variables.

Reading Variables

Substitute a stored value directly in action or description with {{name}}.

from praisonaiagents import Agent, Task

writer = Agent(name="Writer", instructions="Write a report.")

Task(action="Summarise {{research_data}} in three bullets", agent=writer)

Read the same value inside a handler or should_run with ctx.variables["name"].

from praisonaiagents import Task

def summarise(ctx):
    return {"summary": ctx.variables["research_data"][:200]}

Task(name="summarise", handler=summarise)

Best Practices

Name variables for what they hold

Use clear names like research_data or score so downstream {{name}} references read naturally.

Set output_variable on the producing task

Attach output_variable to the task that creates the value, not the one that reads it.

Order dependent tasks with context

Pass context=[producer_task] on the consumer so the team runs them in the right order.

Handler Tasks

Run Python code as a task step

Conditions

Gate tasks with should_run

Workflows

Chain agents into pipelines

Getting Started

Install

Core Concepts

Guides

Features

Models

Databases

Observability

Memory

Telemetry & Analytics

Knowledge

RAG

Persistence

Tools

Other Features

Developers

Configuration

Best Practices

Getting Started (No Code)

Quick Start

How It Works

Reading Variables

Best Practices

Handler Tasks

Conditions

Workflows

​Quick Start

​How It Works

​Reading Variables

​Best Practices

​Related

Handler Tasks

Conditions

Workflows

Quick Start

How It Works

Reading Variables

Best Practices

Related