Free · runs on your computer · inside your coding agent

Meet your app's first 10,000 users before they exist.

dataready reads your app and builds a synthetic community around it: 1,000 to 10,000 people drawn from real-world numbers, with jobs, budgets, devices and habits. Next, it lets them live with your app for 30 days and shows you where they leave, why, and which change to try first.

Install dataready See how it works

How it works

Six steps, in plain words

You talk to your coding agent the way you always do. dataready does the counting on your computer; your agent does the reading and the thinking.

Live today
Map your app

It reads your app's code and writes down what is there: screens, sign-up, plans, trial, paywalls, the moments that matter. Your agent fills in what needs judgement.
map my app
Preview
Meet your community

1,000 to 10,000 people for your app, from real-world numbers per market: ages, incomes, jobs, how handy they are with tech, how price-sensitive, how patient. Every kind of person is covered.
build my community
Preview
Watch 30 days

Each person lives with your app for a month: they arrive, sign up or not, come back or not, hit the paywall, pay or leave. On your computer, in seconds; your agent answers the key moments in character.
simulate 30 days
Preview
Send a sample through the real app

Up to 15 varied people walk your actual app, with your agent driving the browser. Your app has to run on your computer or on a private test address; never production, test sign-ups only. Then say calibrate: where reality and the model disagree, the model is corrected.
send 10 people through my app
Preview
See why people leave

Funnel, retention and conversion per segment, with confidence intervals, the exact step where each group gives up, and the reasons they would give.
why do people leave
Preview
Test the fix

Concrete changes, ranked by how many people they reach and how much they move. Try each one on the same community first, as a synthetic A/B, then share the report: one link and a code.
what should I fix

Everything it shows is a synthetic hypothesis, not real user data: the fastest first opinion you can get, never a substitute for your real customers.

Your dashboard

Your community, in a private page on your computer

Say open the dashboard and your browser shows your app's profile and its community: who they are, how they split by job, income, age, personality, device and market, and each person's card. It runs on your machine, for you only.

The dashboard's Community tab: 10,000 synthetic people in 42 professions across many countries, a yellow banner saying synthetic hypotheses, not real user data, filters, and the first rows of a table of people with name, age, profession, yearly income in their own country's currency, personality, device and channel. — **Community.** Who your 10,000 people are: job, income, age, personality, device and how they found you.

The Simulation tab: 30 days with 10,000 synthetic people, 11.7 percent bought, 25.8 percent active on day 7, a funnel from visited to bought, a chart of how many are still active each day, the median time on each screen by week and the events per day. — **Simulation.** Thirty simulated days: how far people get, and how many are still around a week later.

The Live tab: 5 personas walked the app and its MCP server, a table of the two surfaces, two journeys from the site into the MCP server, and the MCP calls each persona's agent made. — **Live.** A small sample walks your real app, running on your computer, and its MCP server too.

The Analysis tab: why people stay, pay and leave, with 44 claims each backed by evidence, the themes behind the reasons people gave, and short write-ups of where and why people stop. — **Analysis.** Why people stay, pay and leave, every claim with the numbers behind it.

The Recommendations tab: seven changes ranked by reach and impact, then one of them, giving reports more room on the free plan, tested as a synthetic A/B on the same people, with conversion and day-7 retention up and significant. — **Recommendations.** What to change first, ranked, and one change tried on the same people as a synthetic A/B.

Screens from a demo run on a sample app. Synthetic hypotheses, not real user data.

Roadmap

What works today

App ProfileMap your app from its codeLive today
Community1,000–10,000 people, dashboard tabPreview
30 daysSimulated behaviour on your appPreview
Real-app sampleUp to 15 people, app running locally or on a private test addressPreview
CalibrationThe model learns from those walksPreview
Why they leaveFunnel, retention, conversion per segmentPreview
Test the fixRanked changes, synthetic A/BPreview
Share the reportOne link and a code on dataready.si, asked firstPreview

Every step runs today. Preview means it works and we are still polishing it: tell us what you find. Install once and every improvement arrives in the same tool, on the same community.

Your data

Your app never leaves your machine

On your computer

Your code, read only, inside your app's folder. Your app's profile, your community, and everything that comes later, kept in .dataready/ in your project. Your coding agent does all the thinking with the model you already use; we run no AI of our own.

On our side

Your sign-in email. The library of 2,480 archetypes plus the ones people propose, and the know-how: real-world numbers per market and how to read an app. Your computer downloads those; nothing about your app comes back, unless you say share the report: then, after you agree, only the report's summary goes up, behind a link and a code.

Who it is for

You built something. Now you want people to stay.

dataready is for people building on Lovable, Replit, Bolt, Cursor or Claude Code who have an app and real ambitions for it: you want to know who it is for, where they drop off and what to change first, before you spend a month or a budget finding out.

Before launch

See who your app speaks to, and who it leaves out, while changing it is still cheap.

After launch

Few sign-ups, or many who never come back? Look for the step where each group gives up.

Before a big change

A new price page or onboarding: try it on the same community first, then on real people.

Install · one line

Add it to the tool you already use

A small MCP server your coding agent starts by itself, inside your app's folder. Pick your tool, copy the line, sign in with your email once. Free.

Package npx -y --package=https://dataready.si/dl/dataready-launcher.tgz dataready-mcp

Claude Codein your app's folder

claude mcp add dataready -- npx -y --package=https://dataready.si/dl/dataready-launcher.tgz dataready-mcp

For your whole team (writes .mcp.json): claude mcp add -s project dataready -- npx -y --package=https://dataready.si/dl/dataready-launcher.tgz dataready-mcp. Then say map my app; the first time, it opens a sign-in page.

Claude Desktopclaude_desktop_config.json

{"mcpServers":{"dataready":{"command":"npx","args":["-y","--package=https://dataready.si/dl/dataready-launcher.tgz","dataready-mcp","--root","/path/to/your/app"]}}}

Settings → Developer → Edit config. Put your app's folder after --root, then restart Claude Desktop.

Cursor.cursor/mcp.json in your app

{"mcpServers":{"dataready":{"command":"npx","args":["-y","--package=https://dataready.si/dl/dataready-launcher.tgz","dataready-mcp"]}}}

Save the file in your project; Cursor tells dataready which folder it is working in.

Codexin your app's folder

codex mcp add dataready -- npx -y --package=https://dataready.si/dl/dataready-launcher.tgz dataready-mcp

Or in ~/.codex/config.toml: [mcp_servers.dataready], command = "npx", args = ["-y", "--package=https://dataready.si/dl/dataready-launcher.tgz", "dataready-mcp", "--root", "/path/to/your/app"].

Windsurfmcp_config.json

{"mcpServers":{"dataready":{"command":"npx","args":["-y","--package=https://dataready.si/dl/dataready-launcher.tgz","dataready-mcp","--root","/path/to/your/app"]}}}

Settings → Cascade → MCP servers → View raw config, paste, put your app's folder after --root, refresh.

Clinecline_mcp_settings.json

{"mcpServers":{"dataready":{"command":"npx","args":["-y","--package=https://dataready.si/dl/dataready-launcher.tgz","dataready-mcp","--root","/path/to/your/app"]}}}

MCP Servers → Configure → paste, with your app's folder after --root.

Needs Node.js 22.13 or newer. Install once: dataready updates itself when your editor starts it. On Windows, use "command": "cmd" with "args": ["/c", "npx", "-y", "--package=https://dataready.si/dl/dataready-launcher.tgz", "dataready-mcp", …].

The archetypes

Over 2,400 archetypes, each with their own story

Your community's numbers come from real-world distributions; its people borrow their voice from this library. A procurement head who signs off alone, a student on a cracked phone, a CFO who needs proof. Browse them, or propose one we are missing: once approved, it joins the library every new community is matched against.

Browse the archetypes Propose your own

Built with prodready? Test it with dataready.

prodready makes what you built with Lovable, Replit, Cursor or Claude Code safe to put in front of real users. dataready tells you which of those users will stay. Same kind of install, made by the same team.

Visit prodready.si

Questions

Good questions, short answers

Is it really free?

Yes. There is no paid plan and nothing to upgrade to. It runs on your computer and uses the coding agent you already have, so there is nothing for us to charge for.

Are these real people?

No. They are synthetic people, generated from real-world statistics about ages, incomes, jobs, devices and habits in each market. What they tell you is a hypothesis to check, not real user data, and the dashboard says so on every page.

What can I do with it today?

All of it: map your app, build its community of 1,000 to 10,000 people, simulate 30 days, send up to 15 of them through your running app, calibrate, see why people leave, get ranked fixes, test one as a synthetic A/B and share the report. Everything after the map is in preview. The roadmap shows where each step stands.

Do you see my code?

No. dataready runs on your computer, reads only your app's folder (never your .env files or keys) and keeps what it makes in .dataready/ inside your project. None of it is sent to us. From us it downloads the archetypes and the know-how. The one exception is yours to make: share the report shows you exactly what would go (numbers and findings, never code or files) and uploads it only after you agree.

Does it use AI?

Your coding agent does, with the model you already use. dataready itself does the counting: drawing the community, the statistics, the checks. People's words come from templates and archetypes, and when you open a person, your own coding agent writes them in character.

Which tools does it work with?

Claude Code, Claude Desktop, Cursor, Codex, Windsurf and Cline, on macOS, Linux and Windows, with Node.js 22.13 or newer. It does not matter whether you built the app with Lovable, Replit, Bolt or by hand, as long as its code is in a folder on your computer.

Will the walkthroughs touch my live app?

No. Your app has to run on your computer (for example npm run dev) or on a private test address you choose; production addresses are refused. Up to 15 people per run, test sign-ups only, never a real payment, and screenshots stay in .dataready/.

What do you keep?

Your sign-in email, the archetypes people propose, and anonymous page counts. If you also use the separate quick check of a public page, we keep its results for seven days so its report page works. Details are on the privacy page.