Lightning Lessons

How to build a production-ready agent

Hosted by Jason Liu and David Kim

Wed, Oct 8, 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

Building agents: pre-production to production

Key decisions and infrastructure needed to deploy an AI agent that handles real user workloads reliably

What worked (and what didn't) with Loop

Real examples from Braintrust's agent development to avoid common pitfalls and accelerate your build

Evolving agents post-launch

Strategies for iterating on agent capabilities while maintaining stability in a live production environment

Why this topic matters

AI agents are moving from demos to production systems users rely on daily. Learn the practical challenges of building production-ready agents to avoid costly mistakes and ship faster. This bridges experimentation and real-world deployment, giving you a framework to build agents that work at scale.

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. 

David Kim

Design engineer, Braintrust

Engineer turned designer. Passionate about developer tools and experiences.

worked with

Braintrust 🧠
Stitch Fix
Meta
University of Waterloo
New York University

Sign up to join this lesson

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