Case study
A practical build spanning Python, OpenAI APIs, LangChain, Django, Docker.
Overview
A legal drafting prototype for NDAs that demonstrates structured generation and professional review workflows. Sealify uses AI to generate initial drafts from structured inputs while maintaining clear boundaries between AI-generated content and professional legal review — an exercise in responsible AI application design.
Context
Legal document generation is a domain where AI can accelerate drafting but must never replace professional review. Sealify explores this boundary — using structured inputs to generate NDA drafts while making the AI's role transparent and the need for legal review unmistakeable.
Architecture
Structured input forms capture deal terms, which are processed through a generation pipeline that produces a formatted NDA draft. The system explicitly marks AI-generated sections and includes review prompts for legal professionals.
Outcome
A working prototype that demonstrates how AI can accelerate legal workflows while maintaining appropriate human oversight — a pattern applicable to any domain where AI assists but doesn't replace expert judgement.
Related writing
24 February 2026 · 16 min read
A long-form essay on AI ethics, governance, and the historical roots of responsible AI systems.
More projects
Led architecture and delivery of a production-grade RAG chatbot for John Lewis Partnership's internal workforce — from first …
Defined and delivered JUMO's internal ML platform from first principles — a config-driven orchestration layer that scaled model …
Designed and built a real-time model monitoring system at JUMO that reduced data anomaly detection time from weeks …
If you need secure GenAI delivery, RAG engineering, MLOps automation, or production ML systems support, feel free to get in touch.