Health, home and travel decision
Bolty
A competent developer can reproduce a useful subset (import, analysis, simple adaptive plans and run tracking) in a few weeks, but the full polished mobile product, integrated App Store subscription handling, long-term tuned coaching behavior and broad device-edge-case coverage are costly to match.
View on the App Store↗$12.99/mo
$156/yr
Read off the official pricing page.
$100one-off64 h to build
$20/mo6 h/mo upkeep
On cash alone, building overtakes the subscription at 3 seats.
No open-source build does this yet
Nothing published replaces this one, so a replacement starts from an empty file. Here is what it would have to cover.
What a replacement has to do
- Ingest runs, analyze metrics, generate/adapt a training plan, deliver session UI and in-run tracking, accept simple natural-language plan adjustments.
What it still won’t have
- Polished native iOS UX and ongoing App Store polish/updates
- Refined coach logic and tuned analytics developed over many app iterations
- Integrated in-app purchase/subscription handling via App Store
- Cross-device reliability and built-in integrations edge-cases (duplicates, Garmin import quirks)
- Marketing, brand and any user base/community features
What remains hard
- Product polish and ongoing maintenance
First-year cost
Keep paying
Paying is—cheaper in year one.
On cash alone, building overtakes the subscription at 3 seats.
Money you would actually spend
Time you would spend
—
What you would spend
What we assumed
The verdict above measures whether you could build it. This one is only about money.
Runnable build prompt
Build a minimal iOS running-coach app using SwiftUI for the client and a small Node.js backend (Express) hosted on a single Heroku / Render instance. Core features in scope: (1) import activities from Apple Health and a Strava personal-access token endpoint, (2) parse GPX/JSON activities and compute per-km pace, HR zones, cardiac drift and elevation-adjusted pace, (3) auto-detect intervals and label splits, (4) a rule-based weekly training-plan generator that rewrites the next week based on recent runs and user inputs, (5) in-app GPS run tracking with BLE heart-rate sensor support and session start/stop, (6) a simple plain-language intent parser (keyword rules) to accept requests like “ease off this week” and reschedule sessions, (7) basic sharing of a run summary image. Out of scope: advanced machine-learning personalization, voice coaching, multi-device sync beyond Apple Health/Strava, and an App Store subscription flow (use a stubbed premium flag). Include error handling, automated unit tests for parsing/metrics and plan-generation logic, CI to run tests, and basic deployment scripts.
How we checked
How the score was reached
- Partly verdict base52
- Price verified on pricing page+3
- Evidence score55
The base comes from the verdict. Everything under it is a check that either happened or did not, and each one is a fact frozen in this record rather than a judgement made at render time - so the same evidence always produces the same number.
How scoring works →Cited sources · 1
Every page the run actually retrieved.
- official productBolty: AI Running Coach - App Store
Integrity checks
What held up, and what did not.
