Design Agentic AI Systems for Engineers
Paramanantham Harrison
Engineering leader, Agentic AI educator
Design your company's agentic AI system in four hours.
You can build an agent in an afternoon. Designing a system of them is a different job. Which agent does what? Which model does each step need? What does each agent read, and what does it remember? Which tools may it call, where does a human approve, and what happens when a run dies halfway? What will it cost each month?
Most teams answer those questions in production, one incident at a time. In this workshop you answer them on paper first, for one real workflow at your company, using AI mission control as the worked example.
You leave with an architecture you can take to a design review: the roles, the models, the context, the tools, the approvals, the failure plan and the budget.
What you’ll learn
A one-day working session to design a production-grade agentic AI system for your own company, from the agent loop to the token budget.
Map the loop, the harness, the roles and the board for one real workflow.
Decide which steps an agent runs and which stay with people.
Pick a model per role on quality, latency and cost.
Design what each agent reads, remembers and caches.
Scope every tool, place each human approval and plan retries.
Put a token budget on every agent before the first line of code.
Workshop agenda
The System Map
Draw the loop, the harness, the roles and the board for one real workflow at your company.
Roles and Models
Decide which agent does what, and choose a model for each role on quality, latency and cost.
Context and Memory
Design what each agent reads, what it remembers and how its prompt is laid out for the cache.
Tools and Approvals
Scope every tool through an MCP gateway and decide where a human approves.
Failure and Durability
Plan retries, idempotent writes and what happens when a run dies halfway.
The Token Budget
Put a cost on every run and a budget on every agent.
Your Architecture Review
Present your design and get it reviewed live.
Learn directly from Paramanantham
Paramanantham Harrison
Engineering leader, Agentic AI educator
Who this workshop is for
Software engineers about to build their first agentic system at work (you learn to design before you build)
Tech leads and architects who will review agent designs for their team (you learn what to ask and what to reject)
Prerequisites
You have built with an LLM API
You have called a model from code or built a simple agent.
You bring one real workflow
A process at your company you want agents to take on.
No setup needed
This is a design session; you draw, decide and get feedback.
What's included
Live sessions
Learn directly from Paramanantham Harrison in a real-time, interactive format.
Live workshop access
Four hours with Param, designing the system for your own company.
Architecture blueprint
The worked AI mission control design, ready to adapt.
Recordings you keep
The full session, recorded.
Certificate of completion
Share what you designed with your team or on LinkedIn.
Maven Guarantee
Your purchase is backed by the Maven Guarantee.
Frequently asked questions
Maven for Teams
Reimbursement
Get your company to pay
Everything L&D needs: email template, receipts, and certificate of completion.
Get reimbursedTeam discount
Learn with your teammates
Save 20%+ when 2 or more teammates enroll in the same cohort.
Save 20%+ with a teamPrivate cohort
Run a cohort for your org
A dedicated cohort with a custom schedule and curriculum, tailored to your team.
Book a private cohort$297
USD
10am–2pm EST