Systems, notdemonstrations.
Every entry below is a system that was built and run against a real operational problem. Figures on this page are measured, never projected.
10
7
Business Operations
02RFQ Agent
A multi-agent procurement system that watches public tender sources, scores every opportunity against fit, and drafts the proposal.
0–100
LLM fit score per opportunity
Renzo
An AI-first engineering system that accelerates frontend delivery for services teams working across many concurrent client codebases.
Applied Interfaces
03Aurora
A voice AI training tool that simulates donor conversations, so teams can practise the interaction before it costs them a relationship.
30%
Increase in donor conversions
FoodLens Agent
A restaurant photo enhancement agent: a dish photo goes in, marketing-ready imagery comes out.
6
Style presets
21
Pytest tests, TDD throughout
Style Me Agent
AI hairstyle recommendation that reasons from face shape rather than from whatever is trending.
7
Face shapes analysed
4
Style directions per result
None of these started as a product.
They started as an operational problem someone needed solved. If you have one, that is the conversation.