Every production system, filterable.

Portfolio Model Context Protocol Server

stdio MCP server exposing typed tools (get_projects, get_case_study, search_writing) so any compatible client can ground answers in real portfolio data.

Enterprise RAG Document Intelligence System

Architected end-to-end RAG pipeline using Azure OpenAI and Cognitive Search with hybrid retrieval and re-ranking.

Document Processing & Vision AI Pipeline

Built intelligent document processing pipeline using GPT-4 Vision and Azure Form Recognizer.

Arabic ↔ English Statistical Report Translator

Built a GPT-4 translation copilot with a SCAD-specific glossary (UN SDG terms, demographic taxonomies) and a side-by-side reviewer UI.

Smart Meeting Summariser & Action-Item Extractor

Pipeline ingests Teams transcripts, summarises in Arabic + English, extracts owners and deadlines, and posts structured items to Planner.

Inbox Triage & Auto-Reply Drafting Copilot

Outlook add-in that classifies incoming mail by intent, drafts a tone-matched reply, and learns from accept/reject signals.

AI Code-Review Assistant for .NET Repos

GitHub Action that posts inline review comments — security checks, async/await pitfalls, EF Core anti-patterns, and a prompt-injection scanner for any AI-touching files.

Executive Dashboard Narrator

Scheduled job reads dashboard datasets, runs significance tests, and writes a 4-paragraph bilingual executive brief grounded in the actual numbers.

Prompt & RAG Evaluation Harness

Open-source-flavoured eval harness with ~400 graded queries, judge-LLM scoring, and a CI step that blocks regressions in retrieval recall and answer quality.

Internal Policy & HR Q&A Bot

Slim RAG pipeline over the policy library with citation-first answers and an escalation hand-off to a human HR contact.

Statistical Data-Quality Anomaly Detector

Hybrid stats + LLM pipeline: classical outlier detection flags suspect rows, then GPT-4 reasons about whether they're real changes vs. likely data-entry mistakes.

Open-Ended Survey Response Coder

Few-shot Arabic-first LLM coder with confidence thresholds; high-confidence answers auto-coded, low-confidence ones routed to a human-in-the-loop UI.

Smart Form Validator (Arabic Address & Name Parsing)

Light GPT-3.5 normaliser + transliteration model that standardises names, splits address components, and validates them against the national address registry.

Knowledge-Base Auto-Tagger & Linker

Batch embedding + classification pipeline that assigns SDG topics, year, language, and confidentiality tier, plus suggests related documents.

Intelligent Conversational Analytics Platform

Built natural language to SQL query system with conversational interface and automatic error correction.

AI Conversational Chatbot (18K+ Monthly Queries)

Deployed conversational AI chatbot with context-aware multi-turn dialogue and intent routing.

Regulatory & Policy Change Watcher

Daily crawler + LLM diff summariser that posts only material policy changes — with citations — to a Teams channel.

Citizen Service Request Auto-Router

Intent + topic classifier on top of the request text routes to one of 22 specialist teams, with a confidence-gated escalation path.

Real-Time Social Sentiment Engine

Streaming pipeline classifies sentiment + topic, detects spikes, and pushes alerts to subscriber dashboards.

Lease Application Lead Scoring

Logistic-regression scoring model on application + bureau features, exposed as an API into the leasing workflow.