---
title: Your observability tool isn't ready for agents
description: >-
  Why AI agents fail quietly in production and what should belong in your
  observability stack.
date: '2026-08-19'
dateDisplay: 'Wed, Aug 19 · 3:30pm UTC (11:30am EDT)'
duration: 45 min
status: upcoming
tags:
  - Logfire
speakers:
  - Jameson Lee
canonical: 'https://pydantic.dev/events/observability-for-agents'
---

> Markdown version of [Your observability tool isn't ready for agents](https://pydantic.dev/events/observability-for-agents) — the canonical HTML page.
>
> Wed, Aug 19 · 3:30pm UTC (11:30am EDT) · 45 min · Speakers: [Jameson Lee](https://pydantic.dev/authors/jameson-lee.md)
>
> All events: [/events.md](https://pydantic.dev/events.md) · Site index: [/llms.txt](https://pydantic.dev/llms.txt)

---

# Your observability tool isn't ready for agents

Why AI agents fail quietly in production and what should belong in your observability stack.

## What you'll learn

- Why the LLM layer stops being enough
- What stitching tools together costs your team
- Where evals fit, offline and online

## About

You're paying for two observability stacks to watch your agent. One traces the request through your handler and database, and when it reaches the model call, all it sees is a POST that took four seconds. The other has the prompt and tokens, but not the query that returned bad context.

When an agent fails quietly, nothing errors, latency looks fine, and someone on your team spends an afternoon across tabs correlating timestamps.

[Pydantic Logfire](https://pydantic.dev/logfire?utm_source=pydantic.dev&utm_medium=event_page&utm_campaign=observability-for-agents) takes a different approach. It's built on OpenTelemetry, so the model and the system around it belong in the same trace. We'll walk through how that works: what gets instrumented, where the data lands, and what those traces are worth once the incident is over.

A 45-min session, with time for your questions at the end.

## Register

Register on the event page: https://pydantic.dev/events/observability-for-agents