Agentic System Design
Yujian Tang
20k+ Learners on LinkedIn
Designing the Software of the Future
Agents are the new software.
Walk in with a few years of software experience, walk out having participated in a guided agentic design sprint.
This workshop is for you if you've ever faced any of these problems:
You build an agent but it has memory issues in just a few uses
You aren't sure when or why to use MCP, CLI, or APIs
You can't tell where, when, or why your agent is running tools
This is an interactive workshop, so come prepared to not just learn, but to ask and answer questions.
Workshop agenda
Anatomy of an Agent
Agents are not chatbots. In this section, we will cover the three different parts of an agent and how they work. Agent = LLM + Tools + Memory.
Agentic Memory
Agents should be able to remember what they've done, but also need context available for what they are planning and doing.
Multi Agent Systems
Single Agent Applications are so 2025. 2026 and beyond is all about how you can get agents to work together.
Production Readiness
Agent Evals, Reliability, Scalability, Guardrails, Scalability, Logging, and other things to consider and understand for enterprise readiness.
Capstone
Design an enterprise ready agent. Together.
Learn directly from Yujian
Yujian Tang
Founder @ Cracking Gen AI, 20k+ Learners on LinkedIn, Guest Lecturer @ Stanford
Who this workshop is for
Technical professionals building AI Agents in their day-to-day work
Aspiring or current founders building AI Agents for their startups
Non-technical professionals scoping new AI Agent based applications
What's included
Live sessions
Learn directly from Yujian Tang in a real-time, interactive format.
Lifetime access
Go back to course content and recordings whenever you need to.
Community of peers
Stay accountable and share insights with like-minded professionals.
Certificate of completion
Share your new skills with your employer or on LinkedIn.
Maven Guarantee
Your purchase is backed by the Maven Guarantee.
Frequently asked questions
$1,000
USD