MIMIC is a fully autonomous, multi-agent AI framework engineered to transform YouTube tutorial videos directly into deployment-ready software. Rather than simply summarizing a video, MIMIC performs deep visual and auditory forensics, converting raw pixels and audio into a structured 'Stream of Engineering Events' that 6 specialized AI agents use to architect, code, test, and deploy a secure codebase.
0
127
The problem. Teams ship LLM features for contracts without knowing how accurate they are or when a prompt change breaks them.
What I built. A multi-provider eval harness on CUAD contracts (150-example frozen set, 6 clause categories) with bootstrap confidence intervals, an LLM judge validated against human labels, calibration metrics, and a GitHub Actions gate that comments on every PR.
Results. Clause presence F1 0.88-0.90 (95% CI), judge agreement κ = 0.754, ECE 0.053-0.100, 0% parse errors. Found a shared failure mode: all three frontier models truncate the legally operative condition at span boundaries.
Stack. Python, FastAPI, Next.js, Cloud SQL, GitHub Actions, Bedrock, Gemini, Cloud Run.
1
61
building AI-powered healthcare solutions, particularly brain MRI analysis and medical imaging workflows. I can help develop machine learning pipelines for image processing, segmentation, classification, and visualization to support clinical research and radiology workflows. My focus is on building reliable, scalable tools that assist healthcare professionals in analyzing medical imaging data, with appropriate validation and clinical oversight
0
52