Ammar yasir Abdulrahman

Artificial Intelligence Specialization · Cohort 2026

FAHIM: Framework for Arabic Human-centered Interaction on Mobile

FAHIM is an intelligent, voice-driven Android assistant designed to help blind and visually impaired Arabic-speaking users complete multi-step tasks in mobile applications through natural Arabic voice interaction. AI-Driven Planning: Users express their goals through natural Arabic voice commands. The Android application captures and normalizes the current interface using Android Accessibility Services, then sends the user’s request and the observed UI state to a self-hosted LLM-based Planner Server. The Planner dynamically selects the next appropriate UI action, while the Android application validates and executes that action on the device. Iterative Autonomous Execution: FAHIM follows a continuous observe–plan–act loop. After each action, it captures the updated interface and consults the Planner again until the task is completed, clarification is required, or execution must stop. Voice Feedback and User Control: The assistant provides spoken Arabic feedback, asks for clarification when necessary, and requires explicit user confirmation before executing sensitive or externally consequential actions. Privacy-Aware Architecture: UI observation and action execution occur on the Android device, while AI planning is currently performed by a self-hosted remote server rather than an on-device language model. This avoids reliance on third-party commercial LLM APIs, although relevant command and interface data must still be transmitted securely to the Planner Server.

Read the final report (PDF)