Case study · Our products

Daniela – an AI Support App for Women, Developed and Operated by SLAtech

SLAtech developed and operates Daniela, an AI-powered support and self-help app for women aged 18 and older, available in Hebrew and Russian. The product combines a mobile application, backend infrastructure, an administration system and a dedicated website.

Daniela is SLAtech's own product, not a client commission. It is designed for women navigating difficulties in relationships, at work or in their personal lives, offering a space for reflection, supportive conversations and practical self-help.

Daniela is not psychotherapy, does not provide diagnoses and is not a substitute for professional care.

At a glance

The challenge: Create a supportive environment where women can explore difficult situations without an AI system diagnosing them or making decisions on their behalf. The product also needs safeguards for crisis situations and circumstances in which another person might access the user's phone.

What we built: A mobile application with AI-powered conversations, personal memory, difficult-conversation rehearsal, risk assessment for every message, crisis assistance, privacy controls and additional communication-analysis and practical-information features. The solution also includes a backend, administration panel and product website.

The result: A working application and website supported by infrastructure developed, operated and maintained by SLAtech.

The challenge

Discussing relationship problems, workplace difficulties or deeply personal experiences is not always easy. Sometimes there is nobody available to talk to. Sometimes the person closest to the user is part of the problem.

An application in this area needs more than a conversational AI interface. It must distinguish between offering support and making decisions, recognize situations that may require urgent assistance, and reduce the risk of exposing sensitive conversations.

An incorrect crisis contact, an inappropriate response to a situation involving violence, or a private conversation visible to someone else can have real consequences.

For Daniela, safety boundaries are part of the product architecture rather than an afterthought. The system is designed to support reflection and action without claiming to diagnose users or identify every dangerous situation.

What SLAtech built

AI-powered supportive conversations

Daniela provides calm, nonjudgmental conversations. It asks clarifying questions, reflects its understanding of the situation, suggests one coping technique at a time and helps the user identify a small, practical next step.

The application does not impersonate a human, offer medical or psychological diagnoses, or replace professional advice.

Personal memory and continuity

Daniela retains relevant context from earlier conversations so users do not have to repeat their stories each time.

A dedicated interface allows users to review, correct and remove saved information. Personal memory is therefore designed to support continuity while remaining manageable by the user.

Rehearsing difficult conversations

Users can describe someone from their lives and practice a difficult conversation with an AI representation of that person.

After the rehearsal, Daniela provides feedback and allows useful phrases to be saved for reference before a real conversation.

When signs of violence or threats are detected, the system avoids encouraging potentially dangerous confrontation and directs the user toward assistance instead.

Risk assessment and crisis assistance

Every message undergoes a risk check before the ordinary AI response is generated.

The process combines rules for identifying explicit risk-related expressions in Hebrew and Russian with a separate model that evaluates conversational context.

At moderate risk, Daniela may ask about the user's safety and present support contacts. At high risk, the ordinary response is interrupted and a crisis assistance screen appears.

The screen provides country-specific assistance contacts, including resources for Israel and Russia, with one-tap calling. The contact information remains available without an internet connection.

A permanent “I don't feel safe” control also allows users to access assistance without waiting for automatic detection.

Risk assessment is an additional safety measure, not a guarantee that every emergency will be recognized.

Privacy and on-device safety

  • PIN protection: Controls access to the application.
  • Secondary PIN: Opens an empty application view without displaying conversation history.
  • Quick exit: Immediately switches to a neutral screen.
  • Delete everything: Clears information stored on the device through a single action.
  • On-device encryption: Personal information stored on the device is encrypted.
  • Selectable app icon and neutral notifications: Additional options intended to reduce unwanted exposure of app usage.

These measures reduce certain privacy risks but cannot guarantee complete protection in every situation.

Additional capabilities

Screenshot-based conversation analysis: Users can submit screenshots of conversations for analysis to help explore communication patterns and difficult interactions.

AI-initiated messages: The application can initiate communication rather than responding only when the user sends a message.

Practical information and exercises: Content covering subjects such as divorce and workplace rights, intended to support understanding and preparation without replacing legal or professional advice.

Horoscope: An additional content feature that is separate from clinical assessment and crisis risk detection.

Behind the scenes

Separating AI conversations from safety assessment

Daniela does not send each user message directly to its primary conversational model without preliminary checks.

A separate risk-assessment process evaluates the message first. This architecture supports different responses to different risk levels and allows ordinary conversation to be interrupted when crisis assistance is required.

Personal memory management

A background service extracts relevant events and personal context from conversations for use in later interactions.

Users can inspect, edit and remove the saved information.

Hebrew and Russian support

Daniela supports Hebrew, including right-to-left layouts, and Russian. The interface and content are adapted to each language.

Administration and operational controls

SLAtech built an administration system with access controls, two-factor authentication, access logs, account management, crisis-event monitoring and AI usage tracking.

Feature switches provide operational control over product capabilities, while crisis assistance is not subject to disabling through those switches.

Professional consultation

Sensitive content has been reviewed with a consulting psychologist who continues to advise the project. This consultation informs work on content and the boundaries of the application's responses.

Architecture, development and operations

SLAtech is responsible for developing the mobile application, backend, administration system and product website, as well as deployment, infrastructure and technical maintenance.

The development process includes automated testing, error monitoring, AI cost controls and ongoing version management.

Daniela demonstrates how SLAtech brings together product development, backend systems, user experience and AI capabilities while treating privacy and safety as core engineering requirements.

The result

Daniela is an operational product with a working website and application, developed and maintained by SLAtech.

It brings together AI-powered conversations, personal memory, conversation rehearsal, additional content capabilities, privacy features, risk assessment and crisis assistance, supported by dedicated administration and operational infrastructure.

The product does not promise therapeutic outcomes or perfect detection of dangerous situations.

Product website: daniela.app

Frequently asked questions

Is Daniela a form of psychotherapy?

No. Daniela is a support and self-help application. It does not provide diagnoses, replace professional treatment or make personal decisions for its users.

How does Daniela handle messages indicating danger?

Every message undergoes a risk assessment. When high risk is detected, the application displays crisis assistance contacts. This process cannot guarantee that every dangerous situation will be identified.

Are crisis assistance contacts available offline?

Yes. The crisis screen's contact information is accessible without an internet connection. Placing a phone call still depends on telephone service availability.

How does Daniela protect user privacy?

Through PIN access, a secondary PIN that opens an empty view, quick exit, on-device data deletion and encryption of personal information stored on the device.

Which languages does Daniela support?

Hebrew and Russian. The Hebrew interface supports right-to-left layouts.

Who developed and operates Daniela?

Daniela is an SLAtech product. SLAtech developed its application, backend, administration system and website, and manages the technical infrastructure and maintenance.

Building products that require responsibility

SLAtech develops mobile applications, backend systems and AI-powered products where privacy, security and reliability must be considered from the beginning.

Have a complex product or system in mind? Tell us what you want to build.