Files
adk-python/contributing/samples/multi_agent_basic_config/README.md
T
Liang Wu 43f302ce1a chore(config): Add _config suffix to all yaml-based agent examples
Also expand agent folder name to full spelling, e.g. ma --> multi_agent

PiperOrigin-RevId: 795926902
2025-08-16 16:10:43 -07:00

1.1 KiB

Config-based Agent Sample - Learning Assistant

This sample demonstrates a minimal multi-agent setup with a learning assistant that delegates to specialized tutoring agents.

Structure

  • root_agent.yaml - Main learning assistant agent that routes questions to appropriate tutors
  • code_tutor_agent.yaml - Specialized agent for programming and coding questions
  • math_tutor_agent.yaml - Specialized agent for mathematical concepts and problems

Usage

The root agent will automatically delegate:

  • Coding/programming questions → code_tutor_agent
  • Math questions → math_tutor_agent

This example shows how to create a simple multi-agent system without tools, focusing on clear delegation and specialized expertise.

Sample Queries

Coding Questions

"How do I create a for loop in Python?"
"Can you help me debug this function?"
"What are the best practices for variable naming?"

Math Questions

"Can you explain the quadratic formula?"
"How do I solve this algebra problem: 2x + 5 = 15?"
"What's the difference between mean and median?"