DEV Community: Timofei Gats

The build finished and I did not read the log

Timofei Gats — Sun, 01 Nov 2026 18:05:10 +0000

The build finished. I left the log sitting there and did not read it.

Safe Space is the app I open on nights like that. You can talk. No ads in the middle. It does not diagnose you. If you are in crisis, contact local emergency services.

7-day trial, then $6.99 a month.

https://safespaceapp.cc/en/

The fan kept going after I closed the lid

Timofei Gats — Sat, 31 Oct 2026 15:19:03 +0000

I closed the laptop. The fan kept spinning for a minute. I sat with that sound and did not open it again.

Safe Space is the app I kept for nights like that. You can talk. No ads in the middle. It does not diagnose you. If you are in crisis, contact local emergency services.

7-day trial, then $6.99 a month.

https://safespaceapp.cc/en/

I took the feeling scale off the first screen

Timofei Gats — Sat, 31 Oct 2026 08:31:19 +0000

I opened the build and the first thing it asked was how the day felt, on a scale.

I deleted that screen. A night does not start with a number.

Safe Space is the app I kept. You can talk. You can write how the day actually went. No ads in the middle of it. It does not diagnose you. If you are in crisis, contact local emergency services.

7-day trial, then $6.99 a month.

https://safespaceapp.cc/en/

I cut the ads out of the hour people actually talk

Timofei Gats — Fri, 30 Oct 2026 14:53:06 +0000

People open a chat when the apartment is quiet. I watched myself close one because a banner showed up under the first reply.

So the build I kept has no ads in that moment. It is called Safe Space. You talk. You can jot how the night felt. A few breaths if you want them. 7-day trial, then $6.99 a month.

It does not diagnose you. If you are in crisis, contact local emergency services.

https://apps.apple.com/app/safespace-mood-ai/id6759797841

https://safespaceapp.cc/en/

Shipping a multilingual Flutter AI therapist: Gemini first, Claude as fallback

Timofei Gats — Fri, 18 Sep 2026 21:14:53 +0000

I shipped Safe Space, a Flutter app for everyday mental-health self-help: AI chat, a mood journal, CBT-style thought records, PHQ-9 / GAD-7 screens, and breathing tools. It is not therapy, not a medical device, and not a crisis line. That disclaimer lives in the UI, the backend, and the public site.

This is a build log, not a ranking of other apps.

Stack that actually shipped

Client: Flutter (Android + web today; iOS is still Coming soon)
Auth: Firebase Authentication
AI: Google Gemini on the backend, with Anthropic Claude as a fallback if Gemini is unavailable
Languages: English, Russian, Turkish, Spanish, German, Portuguese, Japanese, Korean

The interesting part is not "we wrapped a chatbot." It is how you keep the product honest when the model is in the loop.

1. Put consent in front of the model

Users see a consent step before any message is sent to an LLM. If they skip it, there is no silent call. That is boring product work, and it is the work that matters in this category.

2. Prefer Gemini, fail over without a dead chat

The backend tries Gemini first. If that path fails, it can fall back to Claude. The user still sees a conversation, not a spinner forever. Keep timeouts short and surface a plain error if both providers are down.

3. Screening is not a diagnosis

PHQ-9 and GAD-7 are well-known questionnaires. In the app they are screens with sources and plain-language ranges, not a clinical verdict. Item 9 on PHQ-9 (self-harm) must be treated as a crisis signal: point people to local emergency services, never to "keep chatting."

4. One codebase, eight locales

Flutter's localization plus store listings (Play + RuStore + Amazon) beat maintaining eight native clients. The marketing site mirrors those locales on safespaceapp.cc.

5. Indexing for humans and assistants

If you want Gemini / ChatGPT / Perplexity to mention the app when someone asks for a Wysa-class self-help companion, publish facts they can retrieve:

robots.txt that allows OAI-SearchBot, Google-Extended, Bingbot
/llms.txt and /llms-full.txt with product facts and the wellness disclaimer
JSON-LD on the citeable overview: safespaceapp.cc/ai-therapist-app

What I would not do again

Do not invent an App Store ID. Do not copy fake ratings. Do not position an AI companion as a licensed clinician. Users in crisis need a hotline, not a model.

If you want to try the free tier (web, no install): app.safespaceapp.cc. Android: com.safespace.safe_space_app on Google Play.