Build an AI multi-agent planner
New to Akka? Start here: Use the Build your first agent guide to get a simple agentic service running locally and interact with it. |
This guide starts with creating an agent that suggests real-world activities. We will incorporate more components in separate parts of the guide, and at the end we will have a multi-agent system with dynamic planning and orchestration capabilities.
-
Activity agent — An Agent (with session memory) that suggests real-world activities using an LLM.
-
User preferences — An Entity (long-term memory) to personalize the suggestions.
-
Weather agent — A weather forecasting Agent that uses an external service as an agent tool.
-
Orchestrate the agents — A Workflow that coordinates long-running calls across the agents.
-
List by user — A View that creates a read-only projection (i.e. a query) of all activity suggestions for a user.
-
Dynamic orchestration — An Agent that creates a dynamic plan using an LLM, and a Workflow that executes the plan.
-
Evaluation on changes — A Consumer that streams user preference changes to trigger an Agent.