Class Central is learner-supported. When you buy through links on our site, we may earn an affiliate commission.

YouTube

AI Agent Development Tradeoffs You Need to Know

MLOps.community via YouTube

Overview

Coursera Flash Sale
40% Off Coursera Plus for 3 Months!
Grab it
Learn about critical AI agent development tradeoffs and production challenges in this 57-minute conference talk featuring Sherwood Callaway, tech lead at 11X and former YC founder. Discover how to build digital workers like Alice (an AI sales rep) and Julian (a voice agent) that automate complex sales outreach tasks at scale. Explore the differences between developing voice versus text agents, drawing from real-world experience building voice AI solutions at OpKit. Understand how to implement LangGraph Cloud for agent orchestration, integrate observability tools like Langsmith and Arize for monitoring, and maintain system reliability while preventing hallucinations through regular evaluations. Examine scaling strategies for handling over 1 million prospect interactions monthly across 300+ customers, including partnerships with OpenAI, Anthropic, and LangChain. Gain insights into production-ready agent architecture, API design patterns, monorepo management challenges, and open-source development approaches. Master techniques for tracking agent behavior with OpenTelemetry, running agents locally with Phoenix, and hunting hallucinations in agent traces. Consider the future evolution of AI agent technology stacks and whether current complex architectures will eventually simplify as the field matures.

Syllabus

[00:00] AI Takes Over Health Calls
[05:05] What Can Agents Really Do?
[08:25] Who’s in Charge—User or Agent?
[11:20] Why Graphs Matter in Agents
[15:03] How Complex Should Agents Be?
[18:33] The Hidden Cost of Model Upgrades
[21:57] Inside the LLM Agent Loop
[25:08] Turning Agents into APIs
[29:06] Scaling Agents Without Meltdowns
[30:04] The Monorepo Tangle, Explained
[34:01] Building Agents the Open Source Way
[38:49] What Production-Ready Agents Look Like
[41:23] AI That Fixes Code on Its Own
[43:26] Tracking Agent Behavior with OpenTelemetry
[46:43] Running Agents Locally with Phoenix
[52:55] LangGraph Meets Arise for Agent Control
[53:29] Hunting Hallucinations in Agent Traces
[56:45] Off-Script Insights Worth Hearing

Taught by

MLOps.community

Reviews

Start your review of AI Agent Development Tradeoffs You Need to Know

Never Stop Learning.

Get personalized course recommendations, track subjects and courses with reminders, and more.

Someone learning on their laptop while sitting on the floor.