Building Production AI Agents with MCP & LangGraph

Design, build, and deploy reliable AI agents using the Model Context Protocol and modern orchestration frameworks

Course Format and Delivery

Delivery Method: LiveOnline
Schedule: Full day

All sessions are delivered live by an expert instructor in a fully interactive online environment.

*20% off for group bookings when booking 3 or more attendees from the same organization on the same course dates in the same transaction.

About this course

MCP has become the universal agent-tool connector standard in under 12 months: 97M monthly SDK downloads, 10,000+ servers, SDKs in 7 languages, donated to the Linux Foundation's Agentic AI Foundation (146 member orgs). ServiceNow ships an MCP server (Action Fabric), LangGraph integrates MCP natively, and every major agent framework scores MCP support. Agent reliability has jumped from 20% to 77.3% on Terminal-Bench. Meanwhile, enterprise ROI data is firming up: 171% average return, 6.4 hours/week recovered per seat, with Klarna saving $60M and JPMorgan running 450+ agents daily.

This full-day workshop takes participants from agent architecture fundamentals through building production-grade agents with MCP and LangGraph (126K+ GitHub stars, used in 34% of production architectures at 1,000+ employee companies per Gartner Q1 2026).

Topics Covered

ReAct, plan-and-execute, and multi-agent architectures;
MCP server/client development; LangGraph 0.4+ state machines, conditional routing, and HITL checkpoints;
Tool calling patterns; error handling and retry strategies;
Human-in-the-loop patterns;
and Agent evaluation with LangSmith.
Approximately 35% lecture, 65% hands-on labs.

Brent Laster

Facilitator

Brent Laster is a global trainer, author, speaker, and founder/president of Tech Skills Transformations LLC. He helps enterprise teams adopt modern software practices in AI engineering, AI-assisted development, DevOps, automation, and secure software delivery. He is the author of Learning GitHub Copilot, Learning GitHub Actions, Professional Git, and Jenkins 2: Up and Running, as well as multiple online and live training programs for companies such as O'Reilly. In addition to AI expertise, Brent brings more than 25 years of experience in software development, management and technical leadership, DevOps, release engineering, and open-source technologies. He regularly presents and conducts workshops at industry conferences and for private clients.