An AI SaaS, done right
Building a vertical SaaS with AI from zero to production: spec, stack, tests and deploy — and what's still missing.
An AI SaaS, done right
- Series
- 03
- Class
- 01–04
- Take
- —
- Product
- LexPro
- Host
- Juan
- Guests
- Edixon and Andrés
- 03·01 The spec before the code To record
- 03·02 The boring stack that wins To record
- 03·03 Tests: what makes AI trustworthy To record
- 03·04 From product to first customer To record
LexPro is software for law firms: case management, time tracking and AI-assisted research, on the web and inside Word. AI wrote most of the code; people decided what to build and reviewed every step.
This series isn’t a framework tutorial. It’s the judgment: what you ask AI for, what you review by hand, which tests you need — and the uncomfortable part: there’s no paying firm yet, and we tell it as it happens.
The other series
The framework for working with AI
How a company decides, prioritizes, builds and measures its work with AI — without buying tools before understanding the problem.
Software for property management
How a trade that lives in paper, group chats and spreadsheets — running a residential building — becomes a web and mobile app.
Agents with a human in the loop
Designing work where AI executes and a person approves — and knowing when not to use an agent.
An agent that keeps your books
You tell it what happened and the agent records it, tags it, simulates scenarios and flags patterns. You decide.
An AI seller that gets the meeting
Automated prospecting with judgment: signals, messages and reading replies — all the way to a meeting a person closes.