AI-First Product Builder (AFPB)

AI-First Product Builder (AFPB)

Turn product hypotheses into working experiments, without waiting a sprint from the development team for every insight.

24 hours
En Español

Jan 23rd - Feb 20th

USD 1000USD 800
Early bird price until Jan 8

From USD 295 for Labs subscriptions

For years, figuring out what to build and actually building it were separate capabilities. Product teams researched, prioritized, and specified. Engineering turned those decisions into software.

A PM wrote a ticket and waited for the next sprint. A founder hired a freelancer for every test. A designer validated ideas with screens that could not capture real behavior. A product leader watched discovery slow down because every experiment had to compete with the roadmap.

With coding agents, that boundary is starting to shift. Teams can turn a hypothesis into something a user can actually try, capture signals, and return to the product decision without turning every learning opportunity into a development project first.

Not because this turns everyone into developers, but because it allows someone with strong product judgment to build just enough to learn sooner: a landing page, a functional flow, an automation, a dashboard, a hidden feature, or a pull request ready for review.

This unique program teaches you, week by week, how to use this new building capability as a clear method and incorporate it into your professional product practice. Not to bypass the engineering team, but to enter the conversation with evidence and make better-informed product decisions.

To complete the hands-on exercises in this program, you will need, at a minimum, a Claude Pro subscription (approximately USD 20/month). If you plan to spend significant additional time working on exercises outside of class, you may find it beneficial to temporarily upgrade to Claude Max, although this plan is not a requirement for the program.

In addition to the live sessions, you will need to dedicate an extra 2–3 hours per week to completing exercises.

This program requires prior knowledge of Product Management and/or professional experience working in product roles. If you have any questions about this requirement, please contact us.

What changes when you can build

From idea to experiment: You go from describing what should be built to putting a first version in front of users, leads, or stakeholders.

From mockup to signal: You learn to capture data, feedback, and real behavior—not just opinions about a screen.

From ticket to handoff: You turn a product intention into a concrete change that’s documented, testable, and understandable for whoever reviews it.

From dependency to collaboration: You don’t replace the technical team. You show up better prepared: with context, judgment, clear trade‑offs, and less speculative work to delegate.


After finishing the program you'll be able to close the loop between a product belief, a working experiment, and an evidence‑based decision.

Tools

We will use the following tools

Claude Code
Github
Supabase
Vercel

By the end of the program you will be able to

Measure what you want to learn:* Start with what you want to test, decide which signals to track, build a metrics dashboard, and define the threshold that would make you change your mind.

Build prototypes that capture signals: Turn a screen or idea into a landing page, user flow, or dashboard with persistent data.

Work with Claude Code without losing control: Install, configure, plan, execute, and verify the agent’s work before considering it complete.

Build with basic Full-Stack fundamentals: Integrate authentication, databases, forms, and private dashboards without becoming a developer.

Understand where each component lives and what gets exposed: Distinguish what runs in the browser from what runs on a server, know where credentials must never be stored, and recognize which security decisions should never be delegated to an agent.

Deploy and update a product in production: Make it publicly accessible with a separate production database, and move each change into production through a branch, a staging environment, and a review.

Codify your work rituals: Turn your project context and recurring procedures into a manifest, skills, and sub-agents that the agent can reuse.

Navigate an unfamiliar codebase: Understand how a production application is organized, identify where to make changes, and anticipate risks before editing. You’ll practice this on your own app, treating it as if it were someone else’s.

Prepare a change for review: Create a branch, describe the change, request an assisted review using sub-agents, and prepare a clear, easy-to-review pull request (PR) for the technical team.

Curriculum

1

Getting Started with Your Project

To build with a coding agent, you first need to understand what distinguishes it from a chatbot and how to direct its work. In this module, we will set up your environment and start your own project from scratch. We will also cover how to define what it means for a result to be good and how to verify what the agent produces in different contexts of use. The goal is for you to finish with a working first version of your own project and the judgment needed to guide the agent’s work.
2

Working with Data

A page that only displays information does not allow you to learn from the people who use it. Once your project is up and running, the next step is for it to start retaining information. In this module, we will cover the components that make up a digital product and how they relate to one another. We will also work on how to review and correct what the agent proposes to do before it executes those actions. The goal is to move from requesting changes to making decisions about how your product is built.
3

Architecture and Security

A product can work perfectly and still be exposed. Once your project stores information, you need to understand where each component lives and what is visible to anyone. In this module, we will explore that boundary using your own project. We will also examine which security decisions can be left to the agent and which should not be delegated. The goal is for you to recognize the risks associated with what you build and come to conversations with a technical team equipped with better questions.
4

Users and Rules

When other people start using a product, each person expects to see only their own information and nothing else. In this module, we will cover how to add users to your product and how to protect each user's information. We will also work on how to communicate your project's context and your ways of working to the agent, so you don't have to explain them every time. The goal is to establish two types of rules: those that protect your users and those that guide the agent.
5

Metrics and Learning

An experiment exists to learn something, and that requires defining what number would make you change your mind. With a product that already has users, the next step is to understand what they do. In this module, we will cover how to decide what to measure and how to bring those signals into your product. We will also examine why an agent may start performing worse as you progress and what you can do to prevent it. The goal is to connect what you build with what you want to learn and maintain the quality of your work with the agent.
6

Quality and Sub-Agents

Just because something works doesn't mean it's well built, and reviewing everything on your own doesn't scale. As your product grows, it becomes necessary to add a critical perspective on what has been built. In this module, we will cover what sub-agents are and how to delegate part of that review to them. We will also work on how to prioritize what they find: what needs to be fixed and what can wait. The goal is to improve the quality of what you build while remaining the one who makes the decisions.
7

Deplying

There is a big difference between "it works on my computer" and "anyone can use it." With your product reviewed, the next step is to bridge that gap. In this module, we will cover what it takes to publish your product and what separates the environment where you build it from the one other people use. We will also examine what to do when deployment doesn't go as expected and what changes when everything you do can affect real users. The goal is to make your product available on the internet and enable you to operate it with sound judgment.
8

Working with an existing system

In most professional settings, you don't start from scratch: you work on an existing product with users whose experience must not be disrupted. In this module, using your own product as a practice environment, we will explore how to navigate an unfamiliar codebase and identify where changes need to be made. We will also cover how to introduce changes without disrupting existing users and how to propose those changes in a way that allows a technical team to review them. The goal is to equip you with the judgment needed to contribute effectively to a product already in production.

Program specs

A Learning Path

16 hours of live instruction, organized into 8 modules and combined with hands-on work between sessions. Depending on the cohort, the program is delivered in either 8 two-hour sessions or 4 four-hour sessions.

Three Progressive Stages

The program follows three stages of increasing complexity: building your own product, measuring its performance and reviewing changes with sound judgment, and deploying and updating it as a live production product.

Expected Outcome

You'll leave with hands-on experience across the entire AI-assisted product building process: from an initial landing page to your own deployed product, complete with metrics and a change taken through a branch and pull request (PR) into production.

Frequently Asked Questions

Everything you need to know about this course

Your Instructor

Martin Alaimo

Martin Alaimo

Since 2009, he has worked with more than 200 organizations and supported over 8,000 professionals in their career development journeys.

His approach is situational and hands-on, delivering immersive learning through innovative experiences that enable practical, immediately applicable outcomes—especially in areas often overlooked by traditional academia.

He has spoken at more than 30 conferences across the United States and 14 countries in Latin America and Europe, and is the author of six books on product and digital innovation.

His most recent book, AI Strategy Workshop, provides tools to move beyond the “feature factory” mindset and integrate artificial intelligence with strategic intent and real business impact.

He is the founder of Verica, a platform for running evaluations (Evals) on LLM-based products, designed for organizations that need to measure the quality of the outputs generated by their AI products.

As part of his commitment to innovation, he is an organizing member of Product Tank, the world’s largest Product community.

He is one of the few experts to hold the highest-level certifications in Agile practices: Certified Scrum Trainer (CST), Certified Enterprise Coach (CEC), Certified Team Coach (CTC), Certified Agile Leadership Educator (CAL Educator), and Path to CSP Educator.

Visit his complete professional profile and thought leadership activities on LinkedIn.

Ready to step forward?

You're not starting from zero. You're choosing to advance with purpose.

Learning better is also a decision.