Mozisha
Full-Stack & AI Engineer
About the Project
Mozisha (Taste Engine) is infrastructure for human-led AI orchestration: it captures the moments a person rejects an AI output and turns them into reusable constraints, so hard-won judgment accumulates instead of evaporating. The system is three layers — an MCP server implementing the Model Context Protocol that exposes a single `log_rejection` tool so capture happens inside the editor with zero friction; a core backend holding business logic, permissions and vector search; and a Next.js dashboard with personal and organisational views plus a portfolio generator.
Key Highlights
- Built the capture layer as an MCP server exposing one tool — `log_rejection` — so a rejection is recorded where the work happens rather than in a separate app nobody opens
- Designed the Judgment Loop, a six-step workflow that turns an individual rejection into an encoded, reusable quality constraint
- Implemented vector similarity search so constraints surface by conceptual likeness rather than keyword overlap
- Built a portfolio generator that assembles evidence of expertise directly from validated judgment data
- Designed the Pan-African Constraint Commons for sharing constraints across an organisation and beyond it
Technical Challenges
The product only works if capture is nearly free. Anyone will agree that recording why they rejected an AI output is valuable, and nobody will switch to another tool to do it — which is why the capture layer is an MCP server with a single tool rather than a web form, so the cost of logging a rejection is one call from inside the editor. The modelling problem underneath is harder: 'taste' is tacit, and a constraint is only reusable if it generalises past the specific output that triggered it. Vector search over embeddings is what makes a stored constraint findable later, when the situation rhymes rather than repeats.