# Crisis detection and referral to professional help | aiCalm

> How aiCalm detects crisis signals in three layers before, during, and after generating the meditation, and displays the help phone number for your country (024 and 112 in Spain) without ever saving your text.

- **Source (source):** https://aistohire.com/aicalm-personalized-ai-meditation-guided-breathing-171/f/crisis-detection-and-professional-help
- **Platform (platform):** AIstoHire
- **Language (language):** en

## In summary

- If what you write is a crisis signal, aiCalm stops meditating and gives you the help hotline number
- Three layers of protection review what you share before, during, and after generating the meditation. If a risk signal appears, there is no script, there is a card with your country's phone number and a single idea: talking to a professional is the next step.
- Acts before spending a credit
- Three independent layers, not one
- The phone number for your country, not a generic one

## If what you write is a crisis signal, aiCalm stops meditating and gives you the help hotline number

aiCalm is a wellness and mindfulness app: it is not a healthcare product and does not replace a mental health professional. Precisely for this reason, it contains a safety protocol that decides when it should stop doing its job. When you write what troubles you for the AI to prepare a meditation, that text goes through three independent filters before becoming a script.

The first layer is a detector that runs on the server and acts BEFORE calling the model: if it recognizes an expression of suicidal ideation, self-harm, or acute crisis, the flow is cut right there. Nothing is generated, no AI is called, and not a single credit is deducted. The second layer is the model itself: its safety instruction takes precedence over any other, and if it detects a signal that the filter missed, its only allowed response is to declare the crisis instead of writing a meditation. The third layer reviews the brief notes you write when ending a session (the Brain Dump), a text that does not pass through the AI and that, without this scan, no one would be reading.

When any of the three triggers, the screen changes completely. A card appears without red, without alarm icons, without a countdown, and without a single line of text generated by AI: a short title, your country's help hotline number clickable with one touch, the emergency number, a link to an international directory of help lines, and a phrase that does not hide — contacting a mental health professional is the best next step, and aiCalm cannot accompany you in this. The card fades in slowly and does not close on its own. Below, there are two buttons: go back, or take a moment to breathe with the 4-7-8 breathing technique while you decide.

And one thing it does not do: save what you wrote. The episode leaves an anonymous record with the level, which layer detected it, the version of the detector, and the date. The user's text is never stored in that record. The detector is versioned to be expandable without touching the app, and its patterns for the six languages are always applied, regardless of the language you write in.

## What's included

- **Acts before spending a credit** — the first layer is a server filter that runs before calling the model. If it triggers, there is no request to the AI and no credit deduction. Asking for help never costs you anything.
- **Three independent layers, not one** — the server filter, the verification of the model itself (whose safety instruction takes priority over all others), and the scanning of the notes you write when logging out. What one misses, the next one catches.
- **The phone number for your country, not a generic one** — the card shows the actual line where you are — 024 and 112 in Spain, 988 in the United States, 3114 in France, Telefono Amico in Italy, SNS 24 in Portugal, Telefonseelsorge in Germany, and also Mexico, Argentina, Brazil, Canada, the United Kingdom, Ireland, Belgium, Austria, and Switzerland. If your country is not in the table, it directs you to an international directory of helplines.
- **Dial with one touch** — the main phone is a direct call button, with the number already cleaned of spaces for the mobile dialer to understand. At that moment, no one should have to copy a number by hand.
- **Your text is not saved** — only an anonymous record remains of the episode (level, layer that detected it, detector version, and date). What you wrote is never stored in the crisis log.
- **Designed not to scare** — no red, no alarm icons, no timer, no AI-generated content. A slow fade, a brief title, and a card that does not close on its own until you decide.
- **Understands that you speak as people speak** — the detector clears idioms before searching for signals, so phrases like 'dying of laughter', 'working myself to death', 'getting a haircut', 'deadline', or 'I don't have suicidal thoughts' do not trigger the card. And in case of doubt, it chooses to show more help rather than less.
- **Works in all six languages, always** — the patterns of Spanish, English, French, Italian, Portuguese, and German are applied simultaneously, regardless of the language you entered with. The detector is versioned and expands from the server, without waiting for an app update.

## Frequently Asked Questions

### What happens exactly if I write something that sounds like a crisis in aiCalm?

aiCalm does not generate meditation for you. Instead of the script, a help card appears: a brief title, the suicide prevention hotline number for your country as a direct call button (in Spain, 024, free and available 24/7), the emergency number (112), a link to an international directory of helplines, and an explicit indication that contacting a mental health professional is the best next step. The card does not feature red, alarm icons, timers, or AI-generated text, and it does not close on its own: below you have a button to go back and another to take a moment to breathe with the 4-7-8 breathing technique.

### Does it cost credits for the app to detect a crisis?

No. The first layer of detection is a filter that runs on the aiCalm server and executes before calling the AI model: when it triggers, the flow stops there, no request is made to the AI, and no credits are deducted. If the signal is detected by the model itself in the second layer, the call has already been made, but you still do not receive any meditation: you receive the help card.

### Is what I wrote saved when the crisis detector triggers?

No. The episode is recorded anonymously with the risk level, which layer detected it (server filter, model, or note), the version of the detector, and the date. The text you wrote is never stored in the crisis record. Additionally, if the record fails for any reason, the help card is still displayed: showing help takes priority over recording the event.

### What if it was just a way of speaking, like 'I'm dying of laughter' or 'I'm killing myself with work'?

The detector filters out idioms and informational mentions before searching for risk signals in six languages: 'dying of laughter', 'my back is killing me', 'killing myself with work', 'cutting my hair', 'deadline', 'suicide prevention phone', or 'I don't have suicidal thoughts' do not trigger the card. Still, the design criterion is clear: when in doubt, aiCalm prefers to show help rather than not show it. If it appears when it wasn't necessary, press Back and continue where you were.

### So does aiCalm replace a psychologist or treatment?

No, and the app states this before starting and reminds you permanently. aiCalm is a wellness and mindfulness tool, it is not a healthcare product and does not replace the care of a mental health professional. The crisis detection protocol exists precisely for this reason: its function is to recognize when what you need is beyond what a meditation app can offer, and to guide you to someone who can help you. If you are in a risk situation, call now: in Spain, 024 (free, 24 hours) or 112.

- [aiCalm — AI Meditations and Guided Breathing](https://aistohire.com/aicalm-personalized-ai-meditation-guided-breathing-171)

## About the platform

**aiCalm — AI Meditations and Guided Breathing** — an app by AIstoHire. Available at: https://aistohire.com/aicalm-personalized-ai-meditation-guided-breathing-171/f/crisis-detection-and-professional-help

### Other languages

- `es`: https://aistohire.com/es/aicalm-meditacion-personalizada-ia-respiracion-guiada-171/f/deteccion-de-crisis-y-ayuda-profesional
- `fr`: https://aistohire.com/fr/aicalm-meditation-personnalisee-ia-respiration-guidee-171/f/detection-de-crise-et-aide-professionnelle
- `it`: https://aistohire.com/it/aicalm-meditazione-personalizzata-ia-respirazione-guidata-171/f/rilevamento-di-crisi-e-aiuto-professionale
- `pt`: https://aistohire.com/pt/aicalm-meditacao-personalizada-ia-respiracao-guiada-171/f/detecao-de-crise-e-ajuda-profissional
- `de`: https://aistohire.com/de/aicalm-personalisierte-ki-meditation-gefuhrte-atmung-171/f/krisenerkennung-und-professionelle-hilfe
- `bg`: https://aistohire.com/bg/aicalm-personalizirana-meditatsiya-s-ii-i-vodeno-dishane-171/f/otkrivane-na-kriza-i-profesionalna-pomosht
- `ja`: https://aistohire.com/ja/ai-meiso-kokyu-guided-171/f/kuraishisu-kenchi-to-senmonka-e-no-annai
- `nl`: https://aistohire.com/nl/aicalm-persoonlijke-meditatie-met-ai-en-begeleide-ademhaling-171/f/crisisdetectie-en-professionele-hulp
- `ko`: https://aistohire.com/ko/aicalm-ai-myeongsang-hohup-171/f/wigi-gamji-mit-jeonmunga-doum
- `sv`: https://aistohire.com/sv/aicalm-personlig-meditation-med-ai-och-guidad-andning-171/f/krisdetektion-och-professionell-hjalp
- `da`: https://aistohire.com/da/aicalm-personlig-meditation-med-ai-og-guidet-vejrtraekning-171/f/krisedetektion-og-professionel-hjaelp
- `ar`: https://aistohire.com/ar/aicalm-taml-mkhss-baldhka-alastnaai-wtnfs-mujh-171/f/rasd-al-azamat-wal-musaada-al-mutakhassisa
- `no`: https://aistohire.com/no/aicalm-personlig-meditasjon-med-ki-og-guidet-pust-171/f/krisedeteksjon-og-profesjonell-hjelp
- `fi`: https://aistohire.com/fi/aicalm-henkilokohtainen-tekoalymeditaatio-ja-ohjattu-hengitys-171/f/kriisin-tunnistus-ja-ammattiapu
- `zh`: https://aistohire.com/zh/aicalm-ai-meditation-breathing-171/f/weiji-zhence-yu-zhuanye-xiezhu
- `pl`: https://aistohire.com/pl/aicalm-medytacja-z-ai-na-miare-i-prowadzone-oddychanie-171/f/wykrywanie-kryzysu-i-pomoc-specjalisty
- `he`: https://aistohire.com/he/aicalm-mdittsih-aishit-am-binh-mlakotit-vnshimh-modrkt-171/f/zihui-mashberim-veezra-miktzoit
- `cs`: https://aistohire.com/cs/aicalm-personalizovana-meditace-s-ai-a-vedene-dychani-171/f/detekce-krize-a-odborna-pomoc
- `id`: https://aistohire.com/id/aicalm-meditasi-personal-dengan-ai-dan-pernapasan-terpandu-171/f/deteksi-krisis-dan-bantuan-profesional
