Do I need API experience?

YES! Some API experience is needed for this course. Ideally, you've worked on an API Product already. If you don't have API experience, you can always enroll in API Fundamentals for Product Managers, before taking this course.

I work full-time, what is the expected time commitment?

This will be five live 3-hour sessions over Zoom. The course is delivered over two weeks, and you can optionally book a 1:1 meeting with the instructor. After one month, the group will meet again to show what they have built and get feedback.

What will I actually build?

By the end: (1) two working, deployed MCP servers, (2) an MCP App ready for the ChatGPT or Claude Plugins Directory, and (3) an agent Skill for your product. You'll also have the frameworks and tools to redesign your APIs for agents and to build your roadmap by deciding which agent surfaces to prioritize.

Do I have to take the courses in order?

The ladder is recommended, not required. API Product Mastery for Experienced PMs and this course require API experience and recommend API Fundamentals for Product Managers first if you lack it.

Course

Build What Agents Want: MCP, APIs, Skills & Plugins

Become an Agent Experience (AX) Product Manager, earn your certificate, and build products for agents.

See syllabus and enroll

Maven 100 2026 Taught by Emmanuel Paraskakis

Students enrolled from

Who this is for

Start where this matches your job.

Product Managers taking their product to the next level - so it works when customers start using agents instead of clicking the UI.
Platform and API Leaders deciding which of their APIs to optimize or turn into MCP servers, Plugins and Connectors - and in what order.
Founders & Executives who want to transform their companies and fully leverage AI opportunities and a market of +1.3B users.

What you'll build

Artifacts you can point to after the cohort.

An agent-readiness checklist and an API design Skill.

Two working, deployed MCP servers.

An MCP App ready for the ChatGPT or Claude Plugins Directory.

An agent Skill for your product.

Syllabus

What you'll learn

The 5 things agents want - and one they don't

Map how APIs, MCP, CLI, Plugins and Skills enable agents.
Select the right mix for your product and use cases.
Understand why you should avoid depending on agents scraping your UI.

See your APIs the way agents experience them

Test what works and what doesn't work for agents - in Claude, live.
Watch a live agent skip the docs, guess from training data, and recover from good error design.
Leave with an agent-readiness checklist and an API design Skill - to audit the APIs you have or design the ones you don't.

Build MCP servers two ways - and evaluate them before you ship

Generate an MCP server from an existing API, and then build one from scratch with Replit.
Write the MCP metadata that acts as agent UX, which drives LLM usability - tool names, descriptions, and annotations.
Measure task success rates against prompts to build a baseline so you can establish your own evals.

Plugins, Connectors, MCP Apps - the gateway to 1.3B users

Experience how chat apps render specialized UI right into the conversation with users.
Build a shippable MCP app including its interactive UI using no-code AI tooling.
Get ready to submit, and know what OpenAI and Anthropic require for submission to their directories.

Skills as Onboarding and Documentation

Dissect a Skill's anatomy - the SKILL.md file, progressive disclosure, triggers, and the five product use cases.
Write, security-scan, and test a Skill from scratch for your own product during the session.
Submit your Skill to a directory for customer distribution and understand what drives installs.

Package and distribute your product

Decide which mix of APIs, MCP, CLI, Plugins and Skills is appropriate for your customers.
Assemble your artifacts as Connectors and Plugins and prepare for distribution.
Meet 1:1 with your instructor once the course is over - and then once more with the group to show what you built.

Reviews

What students say

5/5

This class helped me get caught up on the latest software tools and techniques for building and deploying MCP servers, ChatGPT apps, Claude connectors, etc. It's very practical. As these things evolve, I might even take this class again!

Alan

VP of Engineering, Pantheon Sports

5/5

Great content, and very knowledgeable instructor. Highly recommend for any product manager building AI-ready products!

Sajjad

Sr Product Manager, Confluent

5/5

Loved the hands on approach to learning and exposure to various tools to fully automate API life cycle and extending it to create MCP tools. Emanuel is a highly skilled instructor and i am amazed how well informed he is about all new stuff in the industry. Learn from an expert and value the acquaintance with him. Highly recommend the course if you want to set yourself for the next wave of innovation through APIs in the AI first world!

Sarthak

Senior Product Manager, FactSet

5/5

The pace and the material was very relevant. I learned a lot and will be looking into more courses from Emmanuel.

Stig

Product Manager, Thomson Reuters

5/5

I loved the course and the subjectivity with which Emmanuel teaches this course. Loved the pace and depth.

Suyash

Principal Product Manager, Atlassian

Logistics

Cohort details

Enrollment: See Maven
Next cohort: Oct 20, 2026
Workload: This will be five live 3-hour sessions over Zoom. The course is delivered over two weeks, and you can optionally book a 1:1 meeting with the instructor. After one month, the group will meet again to show what they have built and get feedback.
Prerequisites: Some API knowledge is required. This is a fast-paced, hands-on course, and while you don't need to be a coder, it helps to understand HTTP basics or to have shipped an API.
If you need to brush up on your API skills:
Consider taking API Fundamentals for Product Managers first: https://maven.com/emmanuel/api-pm-fundamentals
Some AI experience is expected. We'll walk you through building with LLMs and AI tools, even if you've never used them before. Familiarity with Claude/ChatGPT is a plus.

Fit check

Is this right for me?

Do I need API experience?: YES! Some API experience is needed for this course. Ideally, you've worked on an API Product already. If you don't have API experience, you can always enroll in API Fundamentals for Product Managers, before taking this course.
I work full-time, what is the expected time commitment?: This will be five live 3-hour sessions over Zoom. The course is delivered over two weeks, and you can optionally book a 1:1 meeting with the instructor. After one month, the group will meet again to show what they have built and get feedback.
What will I actually build?: By the end: (1) two working, deployed MCP servers, (2) an MCP App ready for the ChatGPT or Claude Plugins Directory, and (3) an agent Skill for your product. You'll also have the frameworks and tools to redesign your APIs for agents and to build your roadmap by deciding which agent surfaces to prioritize.
Do I have to take the courses in order?: The ladder is recommended, not required. API Product Mastery for Experienced PMs and this course require API experience and recommend API Fundamentals for Product Managers first if you lack it.

Next step

Review the full Maven syllabus.

Team discounts are available on Maven. Training a whole team? Consider the team program.

See syllabus and enroll Compare all courses