---
title: 'Pydantic Online Series: Live and On-Demand Sessions'
description: >-
  Join live and on-demand Pydantic events on Logfire observability, Pydantic AI
  and building reliable AI systems. Learn directly from the team behind
  Pydantic.
canonical: 'https://pydantic.dev/events'
---

> Markdown version of [Pydantic events](https://pydantic.dev/events) — the canonical HTML page.
>
> Site index: [/llms.txt](https://pydantic.dev/llms.txt)

---

# Pydantic events

Join live and on-demand Pydantic events on Logfire observability, Pydantic AI and building reliable AI systems. Learn directly from the team behind Pydantic.

## Upcoming

- [Your agents need a sandbox, not a desert](https://pydantic.dev/events/agents-need-a-sandbox-not-a-desert) — Wed, Jul 29 · 3:30pm UTC (11:30am EDT), 30 min ([markdown](https://pydantic.dev/events/agents-need-a-sandbox-not-a-desert.md))
  Everyone agrees agents need code execution. The agreement ends the moment you ask how. The usual answer is 'my agent needs a full Linux VM to succeed.' That answer suits sandbox providers, and it's often wrong.

## Past (recordings)

- [AI will misbehave. Will you notice?](https://pydantic.dev/events/intro-to-logfire) — Thu, Jun 25 · 3:30pm UTC (11:30am EDT), 45 min ([markdown](https://pydantic.dev/events/intro-to-logfire.md))
  Engineers are shipping AI features fast, often without a dedicated AI specialist. See how to run production AI well with observability across the LLM layer and the whole system, evals before and after you ship, and failures that turn into tests.