AI Capabilities

Ilmiya documents three AI surfaces: ILM (Ilmiya Language Model), the institutional AI suite; Aide, the AI assistant portal for end users; and the Canvas recitation evaluator, which scores Quran recitation in real time. All three are controlled at the Organization level.

ILM

ILM is a suite of AI-driven models that supports teaching through predictive and context-aware automation. Administrators can manage it through Administration → Intelligence.

The ILM dashboard has three main modules:

• Experts: Provides expert-style explanations and academic help.
• Aide: Provides AI assistance for students and staff.
• Usage Analytics: Shows requests, token usage, and performance trends.

Aide

Aide is the main AI interaction area. It supports text chat, file uploads, conversation history, and context across sessions. It also provides real-time voice interaction (RTVI), live voice meetings with barge-in, and selectable domain-specific AI Experts.

Aide also includes Document Mode, which generates editable content in an MDX editor and exports it as .doc files. Additional side-panel tools include Calculator, Drawing Board, Text-to-Speech, and Voice Input.

Canvas Recitation Evaluator

The Canvas evaluator records a learner’s recitation, converts it to text, and compares it word-by-word with the correct Quranic text. It identifies errors and classifies them as Tajweed, Verbal, Waqf, or Memorization.

Results are shown with colour coding:

• 🟢 Correct
• 🔴 Error
• 🟠 Partial

Each attempt is saved with the score, error count, date/time, and audio playback. Judge Mode displays saved errors directly on the Quranic text. Canvas also includes a voice AI assistant for questions and explanations.

Key objects

Object	Definition
ILM	Institutional AI suite; deployed self-hosted or third-party hosted
ILM module	A unit of the ILM dashboard: Experts, Aide, or Usage Analytics
Expert	Pre-configured AI assistant tuned to one domain; published per organization
Conversation	Saved Aide chat session; title auto-generated from the first message
Live meeting	Extended bidirectional audio session with barge-in support
Recitation attempt	One recorded verse with score, error breakdown, timestamp, and audio playback

Configuration

Deployment posture is the primary ILM decision: self-hosted models for full institutional data control and privacy, or third-party hosted models for flexibility and scalability. Administrators manage ILM and review its Usage Analytics from Administration → Intelligence.

End-user availability is feature-gated per Organization:

• Aide as a portal must be enabled by the organization’s administrator.
• Aide_Live gates live voice meetings. Two meeting types are documented — Gemini Live (Google Gemini) and Azure Live (Microsoft Azure Cognitive Services) — and an organization may have one or both, depending on configuration.
• Aide_Chat_Speaker gates the Read Aloud (text-to-speech) control on chat responses.
• Canvas_Recite gates recitation evaluation in Canvas.
• The Experts catalog users can browse is whatever the administrator has published; requests for additional experts go to the administrator.

Constraints and edge cases

• File uploads are capped at 25 MB per file. Supported types: PDF, plain text, PNG, JPG/JPEG, WebP, and CSV. Files are not stored permanently — to reference the same file in a new conversation, upload it again.
• Context from voice sessions is not carried into text chat. If a voice connection drops mid-session, disconnect and reconnect to start a fresh session.
• Live meetings and recitation evaluation stream audio in real time; both degrade on slow or unstable connections, and a recitation evaluation may not complete if the connection drops mid-recording.
• Recitation accuracy depends on a working microphone and a quiet environment.
• Deleting a single conversation is permanent; clearing all history deletes every conversation and cannot be undone.
• Document sessions are stored separately from regular chats, and the editor exports .doc only.
• Voice input (dictation) transcribes a single message into the input field; it is distinct from the voice assistant’s full spoken conversation.

Works with

• Analytics — recitation attempts build the per-verse history surfaced in Canvas statistics; ILM Usage Analytics reports AI request and token volumes.
• Multi-tenant hierarchy — every AI flag above is scoped to one Organization.
• Portal documentation: Intelligence, Aide overview, Chat, Voice, Documents, Experts, Tools, Recitation, Recitation feedback.