For PMs, founders & product teams · PM Live 2026

How I Build
With AI

I'm the CPO of a fintech company. Me and my technical co-founder shipped a full payment platform in 90 days. Today a year after, we keep shipping new features at a rapid pace. This is the exact playbook we use.

90 days to ship
·
2 people
·
15× team equivalent
David Balsam
David Balsam
CPO & Co-Founder, Adesco · Building fintech with AI

Two people. Ninety days.
A full fintech platform.

Hi, I'm David Balsam, Co-Founder and CPO of Adesco. In the past year, two people shipped a full multi-tenant payment platform, a backoffice, third-party APIs, and regulatory compliance. No handoffs. No waiting. No lost momentum.

The old way: I had ideas, five people touched them, users saw them six months later. The new way: my co-founder owns the code, security, and infrastructure. I own product, design, and the customer. We both work in the same codebase, each adding where we're strongest. Everything below is the playbook.

💡

The moment it clicked

I built our early product in Lovable. When we needed to scale, my co-founder rebuilt the architecture in Cursor. At that point he said: why do I rebuild what you can build? He showed me our repo, Supabase, how to branch, how to test on dev. Then he stepped back. I never handed off again.

Two roles. One shared goal.

Every team shipping with AI today divides into two roles. These are not titles. They are ways of working. There are architects, they are in charge of the foundations and security of the codebase. The Builder owns the customer experience of the product. AI is what makes the two of us move fast and like we are a fifteen person team.

Builder

Product · Design · Customer

  • Owns the customer relationship directly
  • Understands the needs and pain points
  • Builds the customer experience
  • Connects all the flows & stakeholders
Architect

Foundations · Security · Infra

  • Sets the repo, environments & CI/CD
  • Owns security, and data integrity
  • Builds complex features in the product
  • Reviews big changes when required
The Architect sets the rails. The Builder builds within them.

The Architect sets the foundations. Before the Builder builds anything.

Product repo
The place where product can build. Branch protection on main.
Branches
PR and CI/CD for every feature. Nothing is deployed wrongfully.
Automated tests
The safety net that lets the Builder move without fear.
Documentation
The collaboration layer between both roles. Shared knowledge and context.

What is the Builder's job?

01

Direct relationship with the customer

Before AI: Customer to PM to Designer to Developer to QA. Two weeks. Translation loses things at every handoff. Today: Customer talks to the Builder directly. The Builder builds the feature that same night. No chain. No delay.

02

Customer experience, end to end

The Builder plans the feature, reviews it with AI, builds it in stages based on the foundations, and tests the result as a user. Every feature passes through these four stages without exception: Plan, Review, Build, Test. No shortcuts.

03

Design language

Screenshot a UI you like and prompt: "Copy this and fit our format." Use shadcn/ui for components. Use 21st.dev for blocks that ship as ready code. The Builder owns consistency across the whole product. No dedicated designer needed.

04

Connecting the dots across the full surface

Marketing page, product, back office, client email, dashboard, CRM. The Builder is the only person who sees the whole picture. Own that view. Make every handoff invisible to the user. And manages the relationships with the stakeholders.

The customer relationship shift

Before AI
Customer
Product Manager
Designer
Developer
QA
Translation loses things. And takes two weeks.
Today
Customer
Builder
That same night.

How the Builder thinks

The mistakes I made when I started weren't technical. They were about how I was thinking about the work. Here's what changed.

01

The prompt is the new spec

Your job isn't to write code. It's to write the brief. Structure every prompt like a spec: what you're building, who it's for, what it should do, what it should look like, what states to handle, and what the constraints are. If you can't explain it clearly, the AI won't build it correctly.

02

Plan first, always

AI doesn't plan ahead unless you do. If you just say "build this," it starts at the top and skips everything else. Prompt to get the structure first, make edits, then implement. Every time I skipped this step, I paid for it later.

03

Build every feature with five states

Default, Loading, Success, Error, Empty. If you only build the success state, you've built half a feature. The other half is what the user sees when something goes wrong. And they always notice.

Every feature. Every time. Default · Loading · Success · Error · Empty
04

When everything collapses, stop

Don't keep prompting into a broken context. Stop. Describe the problem as a user, not as a developer. Get AI feedback on why it's stuck. Start fresh from the plan. This is almost always faster than pushing through.

05

Build once, replicate five times

Every pattern you build (an auth flow, a file upload, a multi-tenant structure) can be replicated. Turn your patterns into reusable prompts. What took two days the first time takes two hours the fifth time.

06

Test like a user, not a builder

Log in. Log out. Go through the whole flow on mobile. Pretend it's your first time. Then try to break it: refresh mid-form, submit strange data, navigate away early. If it handles all of that, you're done.

Structure every prompt like a brief

If you can't explain it clearly, the AI won't build it correctly. These six elements work at the beginning of a project and at the feature level as you go.

WHAT
What you're building
e.g. "A recipient selection screen"
WHO
Who it's for
e.g. "A lawyer under time pressure at 10pm"
PURPOSE
What it should do
e.g. "Fast validation, not a complete form"
DESIGN
What it should look like
e.g. "Here's a screenshot of the competitor"
STATES
All conditions to handle
e.g. "Loading, empty, error, full"
CONSTRAINTS
Technical limits
e.g. "Must work on mobile, RLS enabled"

Five tools. That's it.

I tried a lot of tools. These five stayed. Each one does one thing well, and they connect cleanly.

Cursor

My main coding environment. I write every feature here using AI agents. It reads my codebase, understands context, and follows my custom skills.

Primary IDE

Claude Code

Anthropic's CLI that runs directly in your terminal. It reads your entire codebase, executes commands, edits files, and runs tests. Best for complex multi-step tasks where you need an agent that actually understands context across files.

Agentic CLI

shadcn/ui

Copy-paste UI components built on Tailwind and Radix. You own the code, not a library. Buttons, modals, tables, forms. All consistent, accessible, and easy for Cursor to extend because the code is right there in your project.

UI components

Supabase

The entire backend: auth, database, file storage, edge functions, and Row-Level Security. It's what AWS would be if someone actually designed it for people who aren't backend engineers.

Auth Database Storage Edge Functions RLS

GitHub

Version control and your safety net. Branch for every feature. Commit often. If an AI change breaks something, you go back. If an experiment fails, you go back. Non-negotiable.

Undo button for everything

Six skills I run on every feature

A Cursor skill is a saved instruction set. You run it once, get a structured output, and act on it. Every skill below is free to copy from GitHub. Each one replaces something I used to wait on — a review, a checklist, an update email.

💰

CMO Conversion Review

Point it at any page. Returns a letter grade (A to D), a line-by-line critique of what's killing conversion, and a ranked fix list you can act on in under an hour. I run this before every landing page goes live.

Page Review
✍️

Content Review

Reads every sentence and flags what's vague, off-brand, or too long. Returns specific rewrites, not just direction. Run it on any page, email, or blog post before it goes anywhere a customer might read it.

Page Review
🔍

SEO & AI Citation Review

Runs 12 checks across meta tags, heading structure, internal links, and AI-readability signals. Returns pass/fail on each with a specific fix for every failure. Important now that ChatGPT and Perplexity cite pages directly.

Page Review
🎨

UX / Design Review

Maps friction points by severity. Catches missing feature states (what shows when the list is empty?), accessibility gaps, and mobile issues your eye misses on a desktop screen. Run it after every new UI component.

Page Review
🛡️

Pre-Deploy Checklist

Reads every file that changed before a deploy. Returns GO, NEEDS FIXES, or DO NOT DEPLOY with a specific list of what to address. Built for fintech: catches floating-point money bugs, missing RLS, and cross-app breakage. Runs in about 20 seconds.

Safety
📋

Product Update

Reads your git history and writes a plain-English summary of what shipped. Safe to paste into Slack, drop into a client email, or send to your board. No jargon, no commit hashes. Just what changed and who it helps.

Communication
Copy all skills from GitHub

I lecture at companies building with AI.

This playbook is not just for product teams at startups. I've taken it to companies across Israel and taught their product, tech, and leadership teams how to move faster with AI. If you want me to run a session at your company, fill in your details below and I'll get back to you.

Thanks! I'll be in touch shortly.