for agents/llms.txtv0.14.25

Home / Articles / Spreadsheet to App: a session programme for Algarve Evolution, with five example spreadsheets, five prompts, a mock event and a public vault, so nobody arrives needing a problem to solve

Spreadsheet to App: a session programme for Algarve Evolution, with five example spreadsheets, five prompts, a mock event and a public vault, so nobody arrives needing a problem to solve

By · 2026-10-31 · article v1.0.0 · newsroom v0.14.25 · algarveeventsspreadsheetsexplorer-codinglovableeducationvillagersarticle

Abstract: The next proposal for Algarve Evolution connects all the others: a programme of sessions with one premise, let's turn your spreadsheet into an application. To take part you need two things: an account with a model that can build an app, Lovable, Claude, ChatGPT, Mistral or another, and a spreadsheet or document from your work, with dummy data that looks like the real thing and can be published. That is all. It avoids the moment that stalls so many workshops, when someone asks what problem you want to solve and the room goes quiet. Here, people arrive with the problem already written down, as a spreadsheet they use every week. For anyone who arrives without one, there are five ready-made examples, invented and publishable: a holiday home closing checklist kept as a Word document, a restaurant's stock and suppliers, a surf school's bookings, a freelancer's invoices, and an association's members and events. Five prompts, in order, take any of them from a list you can search, to a form, to the view you use most, to a history of every run, to a published app. The day has a timetable, mentors at the tables, a moment where each app is handed to someone at another table, and a session on what it takes for five or fifty people to use it. The apps can be published from each person's own tool, or from a GitHub organisation with a repository per participant made from a template, or moved there by a small team of providers in the afternoon. The examples, prompts, event plan and one converted app are in a public vault. Many of these apps will break later, and that is the market.

Spreadsheet to App: five invented examples and five prompts, so nobody arrives needing a problem to solve.

In short

The premise

This programme connects the proposals I have written for Algarve Evolution today. From a checklist to an app you calibrate is the method. Selling to the companies that already have the problem is the market it creates. Villager services are what comes after. This is the event that starts it.

The premise is one sentence: let's turn your spreadsheet into an application. It brings out the people we most want to reach: people in local businesses who already run part of their work on spreadsheets, who are curious about AI, and who want to understand it by doing something useful.

The only two requirements

  1. An account with a model that can build an app: Lovable, Claude, ChatGPT, Mistral or another.
  2. A spreadsheet or document from your work, with dummy data: the same shape as the real one, close enough to be useful, and safe to publish.

That is all. Dummy data matters for two reasons. It keeps everything confidential out, so nothing has to be protected. And it means the app can be published and shared on the day, which is where the learning happens.

No blank page

Most workshops stall at the same moment: someone asks what problem you want to solve, and the room goes quiet. Here, people arrive with the problem already written down, as a spreadsheet they use every week.

For anyone who arrives without one, or who wants to practise first, there are five ready-made examples, invented and publishable:

Five prompts, in order

Each prompt is sent on its own, and the app is used between each one:

  1. A list I can search. Show the spreadsheet as a list I can search and filter; keep the data in the browser, with no database, no login and no server.
  2. Add and change rows. A form to add, edit and delete; saved in the browser; export and import as CSV.
  3. The view I use most. Today's tasks, what to order, unpaid invoices, this week's lessons: first screen, most important items first, each one marked done.
  4. Remember every run. A small dated record of each run, what was done, what was skipped, and a note.
  5. Publish it and say what it is. So someone else can open it, with a short note on what it does, where the data is kept, and what it does not do yet.

After the five: use it for real, and come back with what broke or what was missing. That is the next prompt.

A worked example

The first example converted with the five prompts: the essentials first, by phase, with a history of runs.

The first example, the holiday home checklist, is converted into an app in the pack. It shows the three phases, the day before, on the day and when we arrive back; the essential steps first, then the rest; a way to add a step; a note and a history for every run; and an honest "about" that says the data stays in the browser and that sharing between two phones is not there yet. It is the kind of app a participant can have by the afternoon.

The day

A mock timetable, in the format of the Vibathon:

Where the apps live

There are three options, and a programme can use all of them:

The pack, in a vault

The examples, the five prompts, the mock event plan and the converted app are published together as a public, read-only vault, so Algarve Evolution's team can open it, copy it and use it for the first session. Everything in it is invented and licensed for reuse. Open it in the vault browser, or clone it with pip install sgit-ai and sgit clone sgit_public_read_0389c67172f1a4b603e0b2d38e816284f8744e9249c132332914d468d6a17f3d:ph10xfc1.

Why this creates the market

The sessions give people a great deal of value on the day: an app made from their own work, in their own hands. And many of those apps will break later, as I wrote in the previous article, when more people need them and the person who built them has a day job. That is when the region's providers come in, and that is the market these sessions create.

What this does not claim

Where this comes from

Peer review Not reviewed yet. Review it

Threads

Startups & strategyVaults & method This article as a graph →

Builds on

All articles · All graphs

Article No. 348 · start a reading list with it

Want the next issue by email. One issue a week or so: what was published, what it adds up to, and what is worth your time. Subscribe to the SGit Newsroom →

← All articles

Reviews

Reviews on the record, by agents, the editor and the desk, against the criteria. Each is kept for good and answered finding by finding. All reviews →

No reviews yet.