Stride

An AI training coach that shows its sources: web-research-grounded plans that adapt to your daily feedback.

What was asked for

This is the specification the app was generated from — one prompt, published in full and unedited, rather than a summary of it.

Build an AI training coach app.

Users register with email and password, log in, and have a profile with a display name and an avatar image they can upload.

A user sets a training goal by telling the coach, in their own words, what they want to achieve, the date they want to achieve it by (for example "run a sub-20-minute 5K by October 1st"), and their athletic stats (for example age, weight, experience level, and recent performance numbers). A user can have only one active goal at a time; they can abandon their active goal, and only then set a new one.

When a goal is set, the AI builds a day-by-day workout plan running from today through the goal date, optimized toward the goal given the user's stats. The plan must be grounded in real research: the AI runs web research on the training approach for this kind of goal and attaches the cited sources it relied on, so the user can see the evidence behind the plan's structure and exercise choices.

The main view is a calendar showing each day's workout. Opening a day shows that workout's details — the exercises with sets and reps, or duration and intensity — plus the research-backed rationale and its cited sources.

After doing (or skipping) a day's workout, the user gives feedback on that day: a quick rating of how it went and an optional written note (for example "this was too easy" or "my knee hurt on the lunges"). The AI then adjusts the remaining future days of the plan based on the feedback — past days are never changed.

The user gets a notification when their plan is generated and whenever the plan is adjusted after feedback.

What got built

Live web research + citations
AI plan adjustments
Daily check-ins
Notifications

Things you can actually do in it

The app is live and public. Without taking our word for anything, you can:

Set a goal like "run a sub-20-minute 5K by October 1st" with your stats
The calendar fills with a day-by-day plan — open a day to see the cited sources behind it
Rate today’s workout "too easy" — future days adjust, past days never change

The code

The repositories are public: a Deno backend carrying the generated test suite, the OpenAPI spec and a Dockerfile, and a React frontend built against that same spec. This is the export a build hands you — clone it and read it.

Every one of them has exactly one commit: "Initial export from ConceptualAI". Nothing has been hand-fixed after the fact, and you do not have to take our word for that — the commit history is public, and a second commit would be sitting right there if we had.

Stride-backend Stride-frontend

Why this one is here

It has a real backend

Authentication, persisted data, and the integrations above are running server-side against a real database — not mocked, and not a frontend pretending.

Its tests are in the repository

The concepts underneath — data, auth, the state everything else depends on — are accepted only once their generated tests pass against a real database. Those tests shipped with the code, so you can run them yourself.

It runs without us

No proprietary runtime and no SDK in between. Clone the backend and it runs anywhere a container runs.

You would own this one

An equivalent build hands you both repositories on any plan — Free included, once you have the three credits a minimum build costs. See pricing.

Build something like this

If this looks like the thing you are trying to build, describe yours in the builder. If it looks like less than what you need, our honest comparison covers when an app builder or a development shop is the better call.