📌 Executive Concept Summary

This guide details the core technological pillars powering IntelliAssess AI:

1. Form Generator Engine (Prompt-based & File-based generation).
2. Question Libraries & My Uploads (Retrieval-Augmented Generation / RAG).
3. AI Rubrics & Submission Checker (Automated scoring & manual overrides).

1. 🪄 AI Form Generator Engine & Model Selector

The Form Generator allows instructors and test managers to create complete assessments from prompt instructions or reference files.

A. Generation Modes

B. AI Model Architecture & Selection Matrix

IntelliAssess AI integrates with multiple AI providers (OpenAI, Groq, and Gemini) so users can select models based on context window, speed, and accuracy requirements:

C. Supported Question Types & Data Schemas

IntelliAssess AI handles six distinct question formats:

┌──► Multiple Choice (mcq)                  ├──► Multi-Select (multiselect)IntelliAssess AI  ├──► True / False (tf)Question Engine   ├──► Short Answer (short_answer)                  ├──► Fill in the Blanks (fitb)                  └──► Descriptive / Essay (descriptive)

1. Multiple Choice (mcq): Single correct choice with randomized distractor options.
2. Multi-Select (multiselect): Checkbox options requiring candidates to select all correct statements.
3. True / False (tf): Binary boolean evaluation.
4. Short Answer (short_answer): Single-line or brief response matched against model answer keys.
5. Fill in the Blanks (fitb): Sentence stems containing inline blank inputs ([blank1], [blank2]).
6. Descriptive (descriptive): Multi-paragraph open-ended responses auto-evaluated against multi-dimensional rubrics.

2. 📚 Question Libraries & My Uploads (RAG Indexing)

To prevent AI hallucination, IntelliAssess AI uses Retrieval-Augmented Generation (RAG) grounded in your uploaded reference materials.

Document Upload (PDF / DOCX)    │   ▼Background Processing (Celery / Redis Worker)   │   ▼Text Extraction & Semantic Chunking   │   ▼Vector Embeddings (`pgvector` in PostgreSQL)   │   ▼Context-Grounded Question Synthesis

RAG Pipeline Features:

• Background Ingestion Queue: Uploaded files in My Uploads are parsed asynchronously.
• Vector Embeddings (pgvector): Document text is split into semantic chunks and converted into high-dimensional vector embeddings in PostgreSQL.
• Semantic Context Retrieval: During question generation, the AI retrieves the top matching document passages, ensuring all question stems, distractors, and answer keys strictly reflect your uploaded source files.

3. ✍️ Per-Question AI Review Chat (“Generate with Feedback”)

The Generate with Feedback drawer allows users to refine individual questions interactively:

• Individual Question Threads: Open a dedicated AI conversation panel for any question card.
• Refinement Chips: One-click prompt suggestions such as “Make distractors harder”, “Add code formatting”, or “Simplify stem”.
• Safe Merge: Preview AI modifications and merge updates directly into your form without affecting other questions.

4. 📊 AI Rubrics & Submission Evaluation Engine

Automated evaluation in IntelliAssess AI balances AI speed with instructor oversight.

A. Multi-Criteria Rubric Anatomy

When evaluating Descriptive / Essay responses, the AI uses a structured rubric composed of:

• Criteria Tiers: Specific performance dimensions (e.g., Technical Accuracy, Clarity of Argument, Problem Solving).
• Point Distributions: Configurable weight percentages per criterion.
• Supporting Quotes & Evidence: The AI extracts exact quotes from candidate answers to explain why points were awarded or deducted.

B. Submission Checker & Grade Overrides

Candidate Submission   │   ├──► Objective Questions (MCQ, FITB, T/F) ──► Instant Key Matching   │   └──► Descriptive Questions ───────────────► AI Rubric Evaluation                                                    │                                                    ▼                                           Instructor Override Review                                                    │                                                    ▼                                          Final Candidate Scorecard

• Instant Objective Grading: MCQs, Multi-select, True/False, and Fill-in-the-blanks are scored instantly upon submission.
• Rubric-Based Essay Grading: Short answers and essays receive criterion scores and inline feedback notes.
• Manual Overrides: Instructors can override any score item, add manual comments, and recalculate total assessment scores in real time.

🏁 Summary Next Steps

Now that you understand the core concepts, proceed to the step-by-step tutorial: Quick Start: Creating & Inviting Users to Your First Assessment.