---
title: "AI Capabilities | Platform Reference | Ilmiya Documentation"
description: "Ilmiya's three documented AI surfaces — ILM, the Aide assistant portal, and Canvas recitation evaluation — with their deployment options and administrative controls."
url: "https://ilmiya.com/docs/platform/ai-capabilities/"
language: "en"
---

<a id="_top"></a>

# 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.

<a id="ilm"></a>

## 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.

<a id="aide"></a>

### 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**.

<a id="canvas-recitation-evaluator"></a>

### 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.

<a id="key-objects"></a>

## 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 |

<a id="configuration"></a>

## 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.

<a id="constraints-and-edge-cases"></a>

## 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.

<a id="works-with"></a>

## Works with

-   [Analytics](https://ilmiya.com/docs/platform/analytics/) — recitation attempts build the per-verse history surfaced in Canvas statistics; ILM Usage Analytics reports AI request and token volumes.
-   [Multi-tenant hierarchy](https://ilmiya.com/docs/platform/multi-tenant-hierarchy/) — every AI flag above is scoped to one Organization.
-   Portal documentation: [Intelligence](https://ilmiya.com/docs/administration/intelligence/), [Aide overview](https://ilmiya.com/docs/aide/), [Chat](https://ilmiya.com/docs/aide/chat/), [Voice](https://ilmiya.com/docs/aide/voice/), [Documents](https://ilmiya.com/docs/aide/documents/), [Experts](https://ilmiya.com/docs/aide/experts/), [Tools](https://ilmiya.com/docs/aide/tools/), [Recitation](https://ilmiya.com/docs/canvas/recitation/), [Recitation feedback](https://ilmiya.com/docs/canvas/recitation/recitation-feedback/).

[Previous  
Assessments](https://ilmiya.com/docs/platform/assessments/) [Next  
Analytics](https://ilmiya.com/docs/platform/analytics/)

---

[View this page on Ilmiya](https://ilmiya.com/docs/platform/ai-capabilities/) · [All pages in Markdown](https://ilmiya.com/markdown-index.md)