GAIA Benchmark Agent
A deployed multimodal agent that scored 90% (18 of 20) on the GAIA Level 1 final assignment of the Hugging Face AI Agents course. The course pass bar is 30%.
- 90%
- GAIA Level 1 score
- 30%
- course pass bar
- 2
- agent modes
Case studies
Four projects: an agent benchmarked on GAIA, a web app live in production, agent context tooling, and a WebGL2 rendering engine. Each has enough public evidence to discuss the hardest decision and the failure paths.
A deployed multimodal agent that scored 90% (18 of 20) on the GAIA Level 1 final assignment of the Hugging Face AI Agents course. The course pass bar is 30%.
Student roommate-matching web app, live at app.roomeefy.pl since July 27, 2026. All production engineering is mine: auth, database, realtime, CI, and the guards that came out of launch day.
A repo-to-LLM-context tool: clone any repository and flatten it into a file-tree map plus token-aware code artifacts. Ships as a CLI, a FastAPI service, a React dashboard, and an MCP server.
Health and mana orbs for a game UI ("Vessels of Life & Mana"). One fragment shader draws both liquids, six AI-generated art plates provide the vessels, and the whole thing ships as a single self-contained HTML file.