Documentation

What Sapilon is

Sapilon turns a legacy system or an AI-built prototype into production-ready, AWS-native software you own outright, using a governed AI agent whose permissions are written into the code itself.

Your first project

Create a project from the projects list, give it your existing code or a written description as input, and open it. Each project is an isolated workspace with its own repository, wallet draw, and stage.

The four stages

Every project moves through Design (shape, mocked data), Build (real backend on the Build Server), Rehearsal (dress rehearsal on the Rehearsal Server), and Live (production). Each transition is a gate that checks readiness rather than a deploy button.

Your first Ask

Ask for one outcome at a time, say what it is for and what must not change, and read the diff before you accept it. A good brief is the difference between one turn and five.

Naming what you see

Your app's screen is made of named regions (the nav rail, the sidebar, the page header, the main area and the aside panel), and naming the one you mean turns a vague request into a precise one.

Existing System

Answer one question about where your current system lives, and the product gives you a short, ranked list of what to bring, with a plain explanation of what the agent has to guess if you skip each one. Telling us something does not exist is a real answer.

Data migration

Point us at your old data. We read what it holds without copying it, you choose what to bring, and we work out how it fits the new system — every decision written down for you to accept or disagree with. Each run reads the data fresh and loads it; rehearse as often as you like on the Rehearsal Server, read a report that says whether the totals match, and only then go Live. Nothing reaches your Live data without every row being checked first — and, with a Rehearsal Server, drilled there.

Tasks

A task is one piece of work queued for the project, written by you or split out by the agent from a larger request, and it is the record of what is planned rather than the mechanism that does the work.

Plans

A plan is the agent’s written proposal for a change large enough that building it straight away would be a guess: what it understood, the decisions it needs from you, the steps it would take, and the technical approach behind them.

Project history

Every project keeps a record of the agent sessions, releases and review runs behind it, so what changed, when, and at what cost is answerable after the fact rather than reconstructed.

Architecture

Architecture is where you decide how your app runs for real people. Answer how bad a day of downtime would be and what sensitive information it holds, and Sapilon suggests one of three options (Essential, Balanced or Dedicated), priced side by side. Choosing is free until the project moves to Rehearsal. After that, a switch shows its steps before anything starts.

Settings

Settings holds what is about the project itself — its name, its description, keeping it up to date, and switching it off — while everything about the app you are building lives in Explorer.

Sign in with Google

Turn on Sign in with Google on the Authentication page, create an OAuth client in the Google Cloud Console using the two values Sapilon shows you, then paste the client ID and secret back into Sapilon and publish.

Your own web address

Add your address in the Web addresses card on the Publish page, create the two records it gives you at your domain provider, and wait. The Sapilon address keeps working the whole time and afterwards.

Moving the sign-in page

Moving the sign-in page takes about twenty minutes, and nobody can sign in while it runs or until your record has spread. People already signed in stay signed in. Do it out of hours — and Use the Sapilon sign-in address puts it back in one click.

Your iOS app

Publish to Live, open the iOS App page, enter your bundle identifier and Apple Team ID, and choose Create iOS app. Then open ios/App.xcodeproj in Xcode on a Mac, archive it and upload it to App Store Connect. Your web app keeps updating through Publish, with no new App Store release.

Ownership zones explained

Every part of your codebase carries one of three markers, //!AUTO (the agent owns it), //!SAFE (the agent proposes, you approve) and //!DEV (humans only), written in the source itself, so AI permissions are code you can read and change.

Editing generated code

Edit anything you like, and your changes are checkpointed as their own version before the next agent turn, but code you intend to keep hand-writing belongs in //!DEV or //!SAFE, or a later turn may rewrite it.

When the agent stops

A stopped turn is usually governance working as designed: the agent needs an answer, needs your approval on a //!SAFE diff, hit a failing check, or reached an action that requires a verified expert's verdict.

Design

Design settles what the app is: screens, flows, data model and architecture, running against mocked data with nothing deployed, so changing your mind is nearly free.

Build

Build replaces mocked data with a real backend, database and integrations on the Build Server (the first 50 hours are free), so the app works end-to-end before anyone pays for production infrastructure.

Rehearsal

Rehearsal runs the finished app on the Rehearsal Server, where you drill the data migration, walk the real journeys, and check security and running cost while it is still safe to be wrong.

Live

Live is production: the new system takes over, the old one is retired, and the same governed workflow keeps shipping changes with versioning, monitoring and backups behind them.

Promoting between stages

Promotion runs a readiness gate (tests, health, architecture and stage-specific checks) that can pass, pass with warnings, or block; it is a check on the project, not a deploy button.

The servers

A project runs on up to four servers (Design, Build, Rehearsal and Live), each created when the project reaches the stage it serves. Design is free and the first 50 Build Server hours are free; Rehearsal and Live are real standing infrastructure, monitored and backed up, and drawing from the wallet while they exist.

Automated Tests

Tests are generated per feature rather than per file, run on demand on the Build Server, and reported as which features are covered and passing, so the answer to "did that change break anything" is a run rather than an opinion.

Checkup

A checkup looks at three things on one page — whether your project was set up correctly, whether one version of the code is ready to ship, and how the app is protected — and turns what it finds into findings you fix, waive, queue as tasks, or hand to an expert before promoting.

Security

Security is one area of plain-sentence rows — scans, edge protection, access — that keeps being re-checked after promotion, because a dependency that was clean at the gate can become a known vulnerability weeks later.

Accessibility

Every screen your app builds from the Sapilon UI kit is made to meet WCAG 2.2 level AA, and the AAA level for contrast (through High contrast), touch target size, focus appearance and motion. Your own content — images, link wording, video, plain language, custom brand colours — is still yours to get right.

Wallet and top-ups

Sapilon runs on one prepaid wallet that AI points, AWS hosting and expert time all draw from; the first 50 Build Server hours are free, there is no subscription and no seats, and the balance cannot go negative.

Points

A point is Sapilon's fixed-price unit of AI usage with one published rate, so an interaction costs a predictable whole number instead of a token bill you can only understand afterwards.

Costs and usage

Costs & Usage adds up everything one project costs (AI, experts, and the cloud services your deployed app runs on) in one total you can filter by period, category and environment.

What a turn costs

Every agent turn reports what it cost in points and why, so cost is something you read after each turn rather than discover at the end of the month.

Expert work pricing

Expert work is priced by job size: Small (under 30 minutes) and Medium (about an hour) at fixed prices, Large billed hourly against an estimate and a cap you approve before anything starts.