Move from building agents to architecting systems that deliver value
AI can now help with more of the implementation. That makes another skill more valuable: deciding what should be built, how the system should be structured, where humans stay involved, how quality will be measured, and what needs to be true before it reaches production.
Those are architectural decisions.
Become an Agentic Architect is a six-week, project-based program for practitioners who want to move beyond agent experimentation and learn a repeatable way to design and deliver reliable multi-agent systems.
AAMAD: the method behind the course
Frameworks will change. Models will change. Agent runtimes will change. The decisions behind a reliable system do not disappear with the next release. AAMAD gives you a repeatable Agentic SDLC for moving from idea to production:
Build one system you can explain, defend and improve
This is not a collection of lectures. Over six weeks, you will take one agentic use case through AAMAD and turn it into a production-oriented multi-agent capstone.
The final proof is not simply:
“I built an agent”
It is:
“I know why this system is designed this way, how it will behave in production, and what's the value generated”
What you’ll learn
In 6 weeks you will learn a repeatable Agentic SDLC method, build a multi-agent app, and leave as an Agentic Architect
Turn business context into clear requirements, constraints, success criteria and documentation that humans and AI agents can work from
Define agent responsibilities, workflows, context, integrations and system boundaries instead of assembling agents one feature at a time.
Apply the architecture using tools such as CrewAI, Claude Agent SDK, Cursor Agent SDK and other appropriate runtimes without vendor lock-in
Design HITL, observability, evaluation and automated QA into the system instead of treating reliability as something to add at the end.
Deploy the capstone, validate it, present it, and explain the trade-offs behind the system to technical and business stakeholders.
Learn directly from Carmelo
Carmelo Iaria
Agentic Architect, O'Reilly instructor, 30 years of global experience, ex-Cisco
Who this course is for
Technical Builders (Software/AI/Data/Platform Engineers, Tech Leads) that want a repeatable way to deliver reliable agentic applications.
Forward Deployed Engineers working between technical implementation, business requirements and client delivery in Enterprise AI projects.
Product, business and consulting leaders who own the AI outcome and have enough technical curiosity to participate in the capstone build.
Prerequisites
Experience & Background
Own delivery outcomes in tech/product/design/consulting. Read-level Python is helpful; pair with a technical teammate if needed.
APIs & Cloud Platforms
Comfort with Git/GitHub, API basics, and AWS (or similar). If rusty, budget extra setup time in Weeks 1-2.
Required Tools & Access
Agentic IDE (Cursor, Claude Code, GitHub Copilot), Model API credits (~$20+), GitHub account, AWS access (recommended)
What's included
Only in live cohorts
Live sessions
Learn directly from Carmelo Iaria in a real-time, interactive format.
Weekly Capstone Office Hours
Bring the part of your system that is unclear, fragile or blocked and resolve the decision before building further on top of it.
Focused 1:1 support
Get Carmelo’s direct input on private live sessions when a specific architecture, implementation or delivery decision is holding back your capstone.
Live and self-paced cohorts include
Community of peers
Learn with practitioners building real agent systems.
Certificate of completion
Validate production-ready agent architecture skills.
Lifetime access
Rewatch sessions and reuse templates as your project evolves.
Maven Guarantee
Your purchase is backed by the Maven Guarantee.
Course syllabus
12 live sessions • 86 lessons • 10 projects
Week 1
Nov
2
Live Session 1: What are you going to Build and How
Nov
6
Office Hours
Welcome to the course
Select the Use Case for your Capstone Project
Capstone Project - Sprint 1: Define Scope and Context
Resources
Week 2
Nov
9
Live Session 2: Defining Solution Architecture and UX
Nov
13
Office Hours
Solution Design & Architecture
Capstone Project - Sprint 2: Define Solution Architecture
Free resources
Testimonials
- This course cuts through the hype and focuses on what actually matters, production-grade AI systems that deliver measurable business value. The focus on real enterprise use cases and live code reviews sets a new bar for practical AI education.
Sairam Sundaresan
AI Engineering Leader | Author of AI for the Rest of Us | I help engineers land AI roles and companies build valuable products - This is what enterprise AI actually looks like
Paul Iusztin
Senior AI Engineer • Founder @ Decoding AI ~ Building an army of AI agents and teaching you about the process.
The Rise of the Agentic Architect
Quick explainer video about this new critical role in the age of AI assisted coding
Your Learning Journey
One project. One method. Six weeks of progressively stronger architecture decisions.
1. Scope the right problem
Run discovery, define the stakeholder, clarify what “done” means, and document requirements and constraints.
2. Architect the system
Design roles, workflows, context, boundaries and integrations before implementation hardens the wrong assumptions.
3. Build the multi-agent solution
Implement the architecture with the runtime that fits your use case.
4. Add production controls
Integrate HITL, evaluation, observability and automated QA so the system can be trusted beyond a demo.
5. Deliver and defend it
Deploy, validate and present the capstone, including the trade-offs behind the architecture.
Course Overview
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$2,395
USD