Agent Architecture

Understanding how AI agents are structured

Every PraisonAI agent has the same core structure. Understanding it helps you build better agents.

---

The 4 Core Components

1. Instructions

What the agent does and how it behaves

2. LLM (Brain)

The AI model that powers thinking

3. Tools

Functions the agent can call

4. Memory

Remembers past conversations

---

Building an Agent

1. Instructions - Define Purpose

   from praisonaiagents import Agent
   
   agent = Agent(
       instructions="You are a helpful coding assistant"
   )
   
2. LLM - Choose the Brain

   agent = Agent(
       instructions="You are a helpful assistant",
       llm="gpt-4o"  # Or "claude-3", "gemini-pro", etc.
   )
   
3. Tools - Add Capabilities

   def calculate(expression: str) -> str:
       """Calculate a math expression"""
       return str(eval(expression))
   
   agent = Agent(
       instructions="You help with math",
       tools=[calculate]
   )
   
4. Memory - Remember Context

   agent = Agent(
       instructions="You are a personal assistant",
       memory=True  # Remember conversations
   )
   

---

Complete Example

from praisonaiagents import Agent

def search_web(query: str) -> str:
    """Search the web"""
    return f"Results for: {query}"

# Full agent with all components
agent = Agent(
    name="ResearchAssistant",
    instructions="You research topics and provide summaries",
    llm="gpt-4o",
    tools=[search_web],
    memory=True
)

agent.start("Research the latest AI trends")

---

The Agent Loop

Every agent follows this cycle:

Step	What Happens
Receive	Agent gets your message
Think	LLM processes and plans
Act	Uses tools if needed
Respond	Returns the answer

---

Multi-Agent Architecture

Multiple agents can work together:

from praisonaiagents import Agent, AgentTeam

researcher = Agent(instructions="Research topics")
writer = Agent(instructions="Write content")
editor = Agent(instructions="Edit and polish")

team = AgentTeam(agents=[researcher, writer, editor])
team.start()

---

Key Takeaways

Start Simple

Begin with just instructions - add tools and memory later

Choose the Right LLM

GPT-4o for complex tasks, GPT-4o-mini for simple ones

Tools Extend Capabilities

Any Python function can become a tool

Memory Enables Context

Enable memory for multi-turn conversations

---

Next: Agent Instructions

Learn how to write effective instructions for your agents.