Abu hamza Khan
I build and ship AI products from idea to production.
New to Contra
Abu hamza is ready for their next project!
What I built. Real-time speech to text, intent parsing into structured actions, and multi-step browser execution with live status streaming, retries on flaky pages and a session export. Open source on GitHub.
Stack. Node.js, Deepgram, OpenAI, Browserbase, Playwright, Socket.IO (http://Socket.IO).
0
13
The problem. Providers spend hours writing notes after visits.
What I built. Voice dictation and edit-by-voice that produce a structured SOAP note, with ICD-10 code suggestions from embeddings for the provider to approve. Tests written alongside every feature.
Stack. FastAPI, Postgres on AWS RDS, Next.js, Claude, Vapi, AWS.
0
18
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.
0
21
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
26