Experiments

The AI lab.

Hands-on explorations. I don't only write strategy — I build and test.

Agents

AI agents

Role-based multi-agent systems that plan, use tools and coordinate on multi-step tasks.

LLM apps

LLM applications

Prompt engineering, evaluation and AI-assisted workflows built hands-on.

RAG

RAG systems

Retrieval, embeddings and grounding that keep AI answers cited and traceable.

Data

Data products

SQL, Python and R turned into tools — from prioritisation models to dashboards.

Automation

Design → code

Pipelines wiring Figma to AI models to ship coded prototypes fast.

Live

RepositoryAI

A shipped RAG product — grounded, source-cited answers from messy source material.