> ## Documentation Index
> Fetch the complete documentation index at: https://docs.praison.ai/llms.txt
> Use this file to discover all available pages before exploring further.
# Reasoning Agents
> Learn how to create AI agents with advanced reasoning capabilities for complex problem-solving.
```mermaid theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}}
flowchart LR
In[In] --> Agent[AI Agent]
Agent --> Think[Think]
Think --> Decide[Decide]
Decide --> Act[Act]
Act --> Out[Out]
style In fill:#8B0000,color:#fff
style Agent fill:#2E8B57,color:#fff
style Think fill:#2E8B57,color:#fff
style Decide fill:#2E8B57,color:#fff
style Act fill:#2E8B57,color:#fff
style Out fill:#8B0000,color:#fff
```
Learn how to create AI agents with advanced reasoning capabilities for complex problem-solving.
## Quick Start
First, install the PraisonAI Agents package:
```bash theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}}
pip install praisonaiagents
```
Set your OpenAI API key as an environment variable in your terminal:
```bash theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}}
export OPENAI_API_KEY=your_api_key_here
```
Create a new file `app.py` with the basic setup:
```python theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}}
from praisonaiagents import Agent, Task, AgentTeam, Tools
# Create reasoning agent
reasoner = Agent(
role="Problem Solver",
goal="Solve complex problems using logical reasoning",
backstory="Expert in logical analysis and problem-solving",
tools=[Tools.internet_search],
)
# Create task
task = Task(
description="Analyze and solve a complex business problem",
expected_output="Detailed solution with reasoning steps",
agent=reasoner
)
# Create and start the agents
agents = AgentTeam(
agents=[reasoner],
tasks=[task],
process="sequential",
verbose=2
)
# Start execution
result = agents.start()
print(result)
```
Type this in your terminal to run your agents:
```bash theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}}
python app.py
```
Install the PraisonAI package:
```bash theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}}
pip install praisonai
```
Set your OpenAI API key as an environment variable in your terminal:
```bash theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}}
export OPENAI_API_KEY=your_api_key_here
```
Create a new file `agents.yaml` with the basic setup:
```yaml theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}}
framework: praisonai
process: sequential
topic: solve complex business problem
agents: # Canonical: use 'agents' instead of 'roles'
reasoner:
instructions: # Canonical: use 'instructions' instead of 'backstory' Expert in logical analysis and problem-solving.
goal: Solve complex problems using logical reasoning
role: Problem Solver
tools:
- internet_search
tasks:
analysis_task:
description: Analyze and solve a complex business problem.
expected_output: Detailed solution with reasoning steps.
```
Type this in your terminal to run your agents:
```bash theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}}
praisonai agents.yaml
```
**Requirements**
* Python 3.10 or higher
* OpenAI API key. Generate OpenAI API key [here](https://platform.openai.com/api-keys). Use Other models using [this guide](/models).
* Basic understanding of Python
## Understanding Reasoning
Reasoning agents are designed to:
* Break down complex problems into manageable steps
* Apply logical analysis to find solutions
* Explain their thought process and decisions
* Handle uncertainty and incomplete information
## Features
Break complex problems into smaller, manageable parts.
Apply structured thinking to solve problems.
Handle edge cases and recover from errors.
Provide detailed reasoning for decisions.
## Multi-Agent Reasoning
First, install the PraisonAI Agents package:
```bash theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}}
pip install praisonaiagents
```
Set your OpenAI API key as an environment variable in your terminal:
```bash theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}}
export OPENAI_API_KEY=your_api_key_here
```
Create a new file `app.py` with the basic setup:
```python theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}}
from praisonaiagents import Agent, Task, AgentTeam, Tools
# Create first agent for analysis
analyst = Agent(
role="Business Analyst",
goal="Analyze business problems and identify key issues",
backstory="Expert in business analysis and problem identification",
tools=[Tools.internet_search],
)
# Create second agent for solution development
solver = Agent(
role="Solution Architect",
goal="Develop comprehensive solutions to business problems",
backstory="Expert in solution design and implementation",
)
# Create first task
analysis_task = Task(
description="Analyze the current market challenges",
expected_output="Detailed analysis of key issues",
agent=analyst
)
# Create second task
solution_task = Task(
description="Develop solutions for identified challenges",
expected_output="Comprehensive solution strategy",
agent=solver
)
# Create and start the agents
agents = AgentTeam(
agents=[analyst, solver],
tasks=[analysis_task, solution_task],
process="sequential"
)
# Start execution
result = agents.start()
```
Type this in your terminal to run your agents:
```bash theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}}
python app.py
```
Install the PraisonAI package:
```bash theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}}
pip install praisonai
```
Set your OpenAI API key as an environment variable in your terminal:
```bash theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}}
export OPENAI_API_KEY=your_api_key_here
```
Create a new file `agents.yaml` with the basic setup:
```yaml theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}}
framework: praisonai
process: sequential
topic: solve market challenges
agents: # Canonical: use 'agents' instead of 'roles'
analyst:
instructions: # Canonical: use 'instructions' instead of 'backstory' Expert in business analysis and problem identification.
goal: Analyze business problems and identify key issues
role: Business Analyst
tools:
- internet_search
tasks:
analysis_task:
description: Analyze the current market challenges.
expected_output: Detailed analysis of key issues.
solver:
instructions: # Canonical: use 'instructions' instead of 'backstory' Expert in solution design and implementation.
goal: Develop comprehensive solutions to business problems
role: Solution Architect
tasks:
solution_task:
description: Develop solutions for identified challenges.
expected_output: Comprehensive solution strategy.
```
Type this in your terminal to run your agents:
```bash theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}}
praisonai agents.yaml
```
### Configuration Options
```python theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}}
# Create an agent with reasoning configuration
agent = Agent(
role="Problem Solver",
goal="Solve complex problems",
backstory="Expert in problem-solving",
tools=[Tools.internet_search],
# Enable detailed logging
llm="gpt-4o" # Language model to use
)
# Task with reasoning requirements
task = Task(
description="Solve complex problem",
expected_output="Detailed solution",
agent=agent
)
```
## Troubleshooting
If reasoning seems incorrect:
* Check problem description clarity
* Enable verbose mode for debugging
* Review agent configuration
If process flow is unclear:
* Verify task dependencies
* Check agent roles and goals
* Review task descriptions
## Next Steps
Learn about automatically created and managed AI agents
Explore lightweight, focused AI agents
For optimal results, ensure your problem descriptions are clear and provide sufficient context for the reasoning agents.