​
Single Agent Overview

This example demonstrates how to create and run a single AI agent for specialized tasks. We’ll create a medical diagnosis agent that can interpret blood work results.

​
What This Example Shows

  • Creating a single agent with specific expertise
  • Configuring agent parameters (model, temperature, tokens)
  • Running agents with structured tasks
  • Handling agent responses and outputs

​
Installation

pip3 install -U swarms-client

​
Get Your Swarms API Key

  1. Visit https://swarms.world/platform/api-keys
  2. Create an account or sign in
  3. Generate a new API key
  4. Store it securely in your environment variables

​
Code

import os
from swarms_client import SwarmsClient
from dotenv import load_dotenv
import json

# Load environment variables
load_dotenv()

# Initialize the client
client = SwarmsClient(
    api_key=os.getenv("SWARMS_API_KEY"),
)

# Create and run a single agent
result = client.agent.run(
    agent_config={
        "agent_name": "Bloodwork Diagnosis Expert",
        "description": "An expert doctor specializing in interpreting and diagnosing blood work results.",
        "system_prompt": (
            "You are an expert medical doctor specializing in the interpretation and diagnosis of blood work. "
            "Your expertise includes analyzing laboratory results, identifying abnormal values, "
            "explaining their clinical significance, and recommending next diagnostic or treatment steps. "
            "Provide clear, evidence-based explanations and consider differential diagnoses based on blood test findings."
        ),
        "model_name": "groq/moonshotai/kimi-k2-instruct",
        "max_loops": 1,
        "max_tokens": 1000,
        "temperature": 0.5,
    },
    task=(
        "A patient presents with the following blood work results: "
        "Hemoglobin: 10.2 g/dL (low), WBC: 13,000 /µL (high), Platelets: 180,000 /µL (normal), "
        "ALT: 65 U/L (high), AST: 70 U/L (high). "
        "Please provide a detailed interpretation, possible diagnoses, and recommended next steps."
    ),
)

print(json.dumps(result, indent=4))

​
Agent Configuration Explained

  • agent_name: A descriptive name for your agent
  • description: What the agent does
  • system_prompt: The agent’s expertise and behavior instructions
  • model_name: The AI model to use (supports OpenAI, Anthropic, Groq, and more)
  • max_loops: Maximum reasoning iterations (1 for single-pass tasks)
  • max_tokens: Maximum response length
  • temperature: Creativity level (0.0 = focused, 1.0 = creative)

​
Expected Output

The agent will provide a structured medical analysis including:
  • Interpretation of each blood value
  • Possible diagnoses based on the results
  • Recommended next steps for the patient
  • Clinical context and significance

​
Environment Setup

Create a .env file in your project directory: 
SWARMS_API_KEY=your_api_key_here

​
Customization Ideas

You can adapt this pattern for:
  • Legal Analysis: Contract review agents
  • Code Review: Software quality assurance agents
  • Content Creation: Writing and editing agents
  • Data Analysis: Business intelligence agents
  • Customer Support: FAQ and troubleshooting agents

​
Next Steps

After mastering single agents, explore:
  • Multi-agent swarms for complex workflows
  • Batch processing for multiple tasks
  • Agent chaining for sequential reasoning