Projects
Eight projects from 2025 and 2026. Each case study opens with the result, then shows how it works, what was hard, and what it still cannot do.
Scroll to open, or skip to the list
Vision and documents
Generative imaging, table extraction and image checks, each carried through to something a person can use and correct.
- IntelliRoomGenerative visionEdits room photos, places catalogue products into them and builds 3D models from product photos. I built every AI workflow and the catalogue.
- Agent P-DFDocument AIFinds tables in scanned pages, rebuilds their rows and columns, reads the text and opens the result in an editor before export.
- PhotoValidatorApplied visionSorts image batches into valid, invalid and manual review, built during a training task with the faculty's IT team.
Agents
Language models that call tools, run in parallel or share a canvas with you, with their steps kept visible.
- MalWhereAgentic securityA local language model triages Windows executables, calling nine analysis tools one at a time and streaming every step.
- M.A.C.E.Concurrent agentsA Minecraft agent where a supervisor checks for danger every three seconds and can abort the skill the agent is running.
- MoaLLM BoardLearning workspaceYou and an AI agent study side by side on one canvas: it explains, examines you and marks the paper, and searches your notes with an embedding model I distilled for it.
Algorithms and products
A card-game engine that explains itself, and an Arabic-first app people install.
