How Daylogue Uses AI

Daylogue uses AI in several parts of the product. This page explains exactly what the AI does, what it does not do, what data it sees, and how that data is handled at each step. No jargon, no vague reassurances. Just how it actually works.

Using Daylogue without AI

No AI mode stops newly submitted content from being sent to Daylogue's AI and voice services on supported platforms. It is not a local-only mode: entries still sync to and are stored by Daylogue under the Privacy Policy. You can keep using manual journaling, curated prompts, structured check-ins, calendar history, and manual tags. Rules-based patterns are a separate consent choice and use structured fields plus eligible accepted manual tags; sensitive tags are left out.

Chat, guided and voice check-ins, new AI-written Stories and tailored insights, automatic tags, OCR, semantic search, and generated programs stop. Some saved AI-created Stories and generated Programs display a history label on the web; a label is not promised for every historical artifact or platform. Turning AI processing back on applies only to future content; protected history is never backfilled. No AI mode is supported on web, iPhone, and Apple Watch, and account activation is rolling out gradually.

What the AI does

AI powers five specific features in Daylogue:

• Follow-up questions during check-ins. When you check in, the AI reads what you wrote and generates a relevant follow-up question. This is what makes the check-in feel like a conversation instead of a form.
• Mood, energy, and stress extraction. The AI reads your words and identifies signals about how you are feeling. If you say "I barely slept and everything felt hard today," the AI notes low energy and elevated stress without you needing to move a slider.
• Pattern identification. Across days and weeks, the AI looks for recurring themes, correlations between metrics, and shifts in your emotional patterns. This is how Daylogue surfaces observations like "your stress tends to be higher on days when your sleep is below six hours."
• Narrative summaries. The AI reads across multiple check-ins and synthesizes them into a narrative about your recent days. This is not a summary of one entry. It is a synthesis of patterns across time, written in a reflective and warm tone.
• Chromascape color palettes. Based on the emotional tone of your check-in, the AI generates a unique color palette that represents the feeling of your day. This is an expressive feature, not an analytical one.

What the AI does not do

These are firm boundaries, not aspirational goals:

• It is not designed to diagnose. Product rules prohibit condition labels and clinical determinations. AI output can still be wrong, so it should not be treated as medical guidance.
• It is not designed to direct your care. Product rules limit output to observations and reflective questions, not treatment or medical recommendations. AI output can still make mistakes.
• AI processing uses listed service providers. Daylogue sends the content needed for a chosen feature to the subprocessors described in the Privacy Policy. Organization administrators do not receive individual journal entries through team aggregates.
• It receives limited product context. A request can include the current check-in and selected recent metrics or themes needed for that feature. Daylogue stores entries and product outputs as described in the Privacy Policy.
• It is not professional care. Guardrails instruct the AI to stay within self-reflection boundaries, but generated text may be inaccurate. Daylogue is not therapy, medical care, or a crisis service.

How the processing works, step by step

Here is what happens when you complete a check-in that uses AI features:

1. 1.Encryption in transit, with additional legacy paths under review. Data is protected in transit by TLS. Some account and vault paths contain additional encryption components, but coverage and key custody are still being re-verified. They are not presented as protection for every entry or as a promise that Daylogue cannot read synced content. Daylogue is not end-to-end encrypted.
2. 2.Brief decryption for AI processing. For features that require AI (follow-up questions, pattern detection, narratives), an entry held in the vault is briefly decrypted in memory; either way, the entry is sent to the AI provider (AWS Bedrock) over an encrypted connection (TLS 1.3).
3. 3.AI processes and returns results. The AI provider processes the request under Daylogue's configured service terms. Current retention and training commitments are described in the Privacy Policy and subprocessor list; Daylogue does not rely on a blanket claim that no provider-side operational record can exist.
4. 4.Results are stored server-side. The AI-generated results (pattern observations, narrative text, extracted metrics) are stored unencrypted in the database, since they need to be readable server-side to power those features.

What data the AI sees

During processing, the AI receives:

• The text of your current check-in (during processing only)
• Your recent mood, energy, and stress history (for context when generating patterns)
• Your themes (for relevance in follow-up questions and narrative generation)

Generative requests are designed to minimize direct identifiers. Voice-session infrastructure may use an account-scoped identifier so Daylogue can bind policy and revoke access safely. Provider handling follows the current service configuration and subprocessor disclosures.

AI training: a firm policy

Daylogue does not use your entries to train its own models. Third-party handling follows the current service configuration, written terms, and subprocessor disclosures.

AWS Bedrock is one of Daylogue's AI providers. Its handling of customer data follows Daylogue's current configuration and written terms, which are tracked in the subprocessor disclosures.

The voice processing path

Voice check-ins use a separate processing path from text check-ins. Here is how it works:

• Audio is streamed to ElevenLabs in real time for voice interaction. Current provider retention terms are listed in the Privacy Policy and subprocessor list.
• Transcription happens within the live session. The resulting check-in text and provider handling follow the terms described in the Privacy Policy and subprocessor list.
• The resulting check-in text (what you said, transcribed) follows the same encryption and AI processing path as a typed check-in.