A charging session was turned down to 7 kW
A fact, in the past tense and in your words. Nothing is ever overwritten: the full history stays, and every later question can be answered from it.
How it works
From your business idea to a first version in the cloud
A pilot usually takes months, and every change afterwards is a new project. Here you describe your business in your own words, see it before it is built, and have a first version running the same day, in your own cloud within a week.
See all seven steps on one example: Amperia →
Today the tools run in Visual Studio Code, and we use them with you; from 2027 the self-service platform makes them usable fully in the browser.
Seven steps, each answering a problem you have today
-
Say what your business needs
“We know what we need, but we cannot write it down the way IT wants it.”
You describe your business in your own words: a short written brief, or a workshop with the people who run the process. The tool asks what it needs to know.
What AI does: turns your sentences into a structure, proposes answers and asks for what is missing. Where you said nothing, it asks instead of inventing a rule.
-
See it before it is built
“We only find out at the end that we were misunderstood.”
Your process as a story and a timeline, a map of the whole, the life of each thing you handle, and the screens each person will see. Everyone in the room can point at a picture and say “that is wrong”.
What AI does: proposes how to split the work into parts and suggests ideas you did not ask for. You choose.
-
Try it the same day
“A pilot takes months, and by then the need has changed.”
A first version runs on a laptop: forms, lists, boards, sign-in with roles, and your own examples as checks that pass. The people who run the process enter real cases.
What AI does: writes the logic of each decision and keeps correcting it until your examples pass. Where your description is silent, it stops and asks.
-
A first version in the cloud
“For a real system we need servers, an infrastructure team and a budget.”
Within a week the first version is reachable from anywhere, in a cloud account you own, with an address and sign-ins for your people. There are no servers to look after.
What AI does: is not needed here: putting the app in the cloud is generated and repeatable, not improvised.
-
Run it without an operations team
“Who watches it at night, and who notices when something breaks?”
You get an e-mail when the app needs you, one screen with the map of your app and its health, and a record of every change that was deployed.
What AI does: will explain an alarm and summarise what happened. This is on the roadmap.
-
Change it when your business changes
“Every change to our software is a new project.”
A change is a new version of your description. Before anything is built, you see what is now and what will change. The history of every decision stays.
What AI does: proposes the changed sentences and shows what a change touches. You decide.
-
Move it where you must Roadmap
“We may need a sovereign cloud or our own data centre later.”
The same app on another platform, without being rewritten. The code moves unchanged; moving your data with it is a service we do with you.
What AI does: is not needed here.
The building blocks
Every description, however large the business, is made of three kinds of line. Written in your own words, each one becomes a part of the software.
Only a flexible session may be turned down
A rule that says, from what has happened so far, whether something may be done and what happens then. Your examples pin it down and run as tests.
Operations see every session in the grid area; a driver sees only their own
What a person needs on a screen, kept up to date by itself as things happen, and shown only to those who may see it.
Larger blocks for larger systems
The same three kinds of line, grouped as the business grows. Each block stays small enough to understand and to check on its own.
One line, as software
Each line of the description becomes one part: a decision with what it records, or a view. Amperia’s “turn a session down” is one part.
A piece of a process, kept together
Parts that belong together: everything about grid calls, from asking to answering to settling.
One job of the business
Several chapters with one purpose, which one team can own and which runs on its own. Amperia has two: Charging and Flexibility.
What crosses between systems
Systems talk only through a contract. Charging reports sessions starting and ending; Flexibility asks it to turn a session down. Charging never hears of a grid call.
The systems together
Amperia is two systems and the contract between them, from one description. A new job of the business becomes a new system beside the others.
Because every block is small and checked on its own, a change stays where it belongs, teams can work side by side, and ready-made blocks of every size can be taken from the marketplace or offered on it.
AI helps. You decide.
One rule holds in every step, and it is why the result can be trusted.
AI proposes
It turns your words into a structure and suggests what is missing. Nothing it proposes counts until you accept it.
People decide
You and the people who run the process decide every rule. Where your description is silent, the tool asks you.
The app records
Every decision your business makes is kept as a record, so you can always answer who decided what, when and why.
Not vibe coding
An AI can write an app this afternoon. Ours writes too, but everything it writes is checked against the rules your business agreed, it asks when it does not know, and it keeps a record of every decision. That does not matter on day one. It matters the tenth time you change it, the day your data matters, and the day the person who built it leaves.
Fast does not mean less
Building software is no longer the expensive part. Knowing what to build, and keeping it right, is. Your money goes to understanding your process and to software that keeps fitting it, not to people typing code.
The hard part is knowing what to build
The software comes quickly because the days with the people who know your process came first. What happens on a Friday evening, who may override a price, which exception matters: that comes from people, not from a prompt.
Speed lowers your risk
You see your own process running before you commit to more than a workshop. If it is wrong, changing it costs a sentence, not a project.
A first version is not finished software
It runs the main path. Daily use needs the exceptions found while you try it, your existing data, sign-ins for your people and a safe way to go live. That is what the next steps are for.
What you keep, whatever you decide
The code
Ordinary code in a repository you own, built on an open-source framework.
The model
Your process described in your own words, readable by your staff, an auditor or a successor.
The book of your app
What the software does, from the whole to the parts, written for the people who were in the room.
Your data
In your own cloud account, in open formats, with the history of every decision.
Your own AI, on your own machines
On the roadmap: running the AI on a model you host yourself, so your descriptions and records never leave your machines and the cost does not grow with use. The guardrails that check every result are why it does not need the largest models.
Find out if Reventless fits
A short conversation is enough to see whether your business process and Reventless are a match — no obligation.
Free 30-minute intro call — no obligation.