# Building AI agents

<Callout title="Governing MCP across your organization?" type="info">
  Speakeasy's [AI control plane](/product/ai-control-plane) connects, secures, and observes every agent and MCP server from one entry point — with SSO, RBAC, runtime guardrails, and a full audit trail.
</Callout>

MCP gives AI agents a standard way to reach the tools and data they need. These guides cover what agents are, where they help, and how to structure agentic applications.

- [Introduction to AI agents](/mcp/using-mcp/ai-agents/introduction) — what AI agents are and how they work.
- [Use cases for AI agents](/mcp/using-mcp/ai-agents/agent-use-cases) — how agents improve existing systems.
- [Agent architecture patterns](/mcp/using-mcp/ai-agents/architecture-patterns) — a practical guide to the architectures of agentic applications.