# [Workshop] Building and Monitoring AI Agents and MCP servers

> ​See how Agent Tracing gives you a better look at all things model usage, call duration, prompting, and more

**URL:** https://sentry.io/resources/building-and-monitoring-ai-agents/

---

**Type:** Video | **Date:** Available On Demand

**Presented by:** Cody De Arkland

Whether you’re building agents in your applications, or standing up an MCP server because its the new cool thing, working with AI is just **different**. Trying to figure out why *it does the weird things it does* is hard. 

​Fortunately, we’ve built a few thing to make this much easier on you. In this workshop, we show you can… 

- ​See how [Agent Tracing](https://sentry.io/product/tracing/ai-agent/) gives you a better look at all things model usage, call duration, prompting, and more
- ​Go under the hood with MCP Monitoring - and learn how to debug client connection issues, tool call performance, transports, and all things MCP 
- ​When things start breaking, use Seer, Sentry's AI Debugging Agent to troubleshoot those vague issues that are crashing and get help from a team of robots using Sentry’s AI PR Review

Follow along with [this guide. ](https://sentry-build-ai.sentry.dev/quickstart/?mkt_tok=Nzc2LU1KTi01MDEAAAGdFjZoycZmmCilOWd6fgcRzBaVwCexEL2KnYPDWOfzx-Q1WBzQNqMcYy7U8zZX47OA4i8b3HLVZfA2kLWgvA)

---

*Source: [sentry.io/resources/building-and-monitoring-ai-agents/](https://sentry.io/resources/building-and-monitoring-ai-agents/)*