Building Durable Agents with Pydantic AI

Lightning Lessons

Practical skills & tools to accelerate your career

Building Durable Agents with Pydantic AI

Hosted by Jason Liu and Samuel Colvin

Wed, Oct 15, 2025

6:00 PM UTC (1 hour)

Virtual (Zoom)

Free to join

By continuing, you agree to Maven's Terms and Privacy Policy.

Invite your network

Go deeper with a course

Systematically Improving RAG Applications

Jason Liu

View syllabus

Wed, Oct 15, 2025

6:00 PM UTC (1 hour)

Virtual (Zoom)

Free to join

Invite your network

Go deeper with a course

Systematically Improving RAG Applications

Jason Liu

View syllabus

What you'll learn

Design Long-Running Agent Workflows

Build agents that run for hours with state management and streaming results using durable execution.

Integrate Pydantic AI with Temporal

Implement production-ready agents using Pydantic AI's temporal integration for job tracking and monitoring.

Move Beyond Chat-Based Agent Limits

Identify when to use durable vs. chat interfaces and architect agents for real economic value creation.

Why this topic matters

Most AI agents today are limited to simple chat interactions that can't handle real-world business workflows. This talk teaches you to build production-grade agents that run complex, multi-step processes over hours—unlocking genuine economic value beyond demos. You'll learn durable execution patterns that transform AI from novelty to practical business tool.

You'll learn from

Jason Liu

Consultant at the intersection of Information Retrieval and AI

Jason has built search and recommendation systems for the past 6 years. He has consulted and advised a dozens startups in the last year to improve their RAG systems. He is the creator of the Instructor Python library.

Samuel Colvin

Founder, Pydantic

Samuel Colvin is the creator of Pydantic, a massively popular data validation library in Python, and now is the founder of Pydantic AI that has built both logfire, an observability tool, as well as Pydantic AI, the best way of creating agents using Python

worked with