Challenge 4: Agent Symphony
Previous Challenge Next Challenge
Introduction
Breaking down complex problems into smaller, manageable sub-problems is a well-established strategy in software development. Multi-agent systems apply this principle to AI, allowing specialized agents to handle specific aspects of a larger task.
In this challenge we’ll introduce the concept of sub-agents and workflow agents which are specialized agents that control the execution flow of its sub-agents.
Note
Workflow agents (sequential, parallel, loop) can be useful for orchestration in many cases as they’re reliable, well structured and predictable. However, it’s also possible to use LLM based Agents for orchestration if more flexibility is needed. In that case you’ll be defining the order and conditions for running the sub-agents in the agent’s instructions (the prompt).
Description
Create two new agents, resource_monitor_agent
which should filter the list of resources found by the resource_scanner_agent
, and store that into the session store as idle_resources
using the appropriate schema. This agent should return back only the instances that are idle.
Then create a new sequential agent orchestrator_agent
that calls the resource_scanner_agent
and the resource_monitor_agent
in sequence. Once you have created the new agents, update the root_agent
to be the orchestrator_agent
.
Note
This is a very basic scenario where we’re looking up basic stats and letting the Agent to decide what’s idle. The power of the LLM based agents is however that they can also detect more advanced patterns based on more complex data (which is beyond the scope of this challenge)
Success Criteria
- The Agent runs both
resource_scanner_agent
andresource_monitor_agent
in sequence and updates the session store. - The session state contains
gce-dev-lnx-tomcat-001
,gce-dev-lnx-tomcat-002
andgce-sbx-lnx-blob-001
(and their details) foridle_resources
using the correct schema when prompted to find the idle resources. - The changes have been pushed to the remote Git repository.
Learning Resources
- Multi-Agent Systems in ADK
- If idle resource list is not generated correctly, make your instructions more specific
Tips
- You can use
adk web
UI to view the agents involved.