Agents
Build an operating model for AI agents that connects development, tool use, evaluation, tracing, and production feedback.
4 guides · Suggested reading order
Start here
The AI agent lifecycle
Explore the development, evaluation, and observation loop.
Continue the learning path
How to evaluate AI agents
Define success for outcomes, actions, and efficiency.
AI agent tracing: How to debug tools, loops, and handoffs
Follow model calls, tool use, loops, and handoffs.
MCP observability: Monitor tools, resources, and context
Inspect context and operations across MCP clients and servers.
Go deeper
Put the foundations into practice
Explore practical guides and resources to take the next step.