Services · Nairobi, Kenya · Remote worldwide
Seven ways companies work with me, from a first AI agent to the backend it runs on and the security review before launch. Each one ends with something that works and a team that owns it.
AI agent development
An agent is easy to demo and hard to trust.
02RAG & knowledge systems
Most RAG systems fail quietly: they retrieve the wrong passage and the model answers confidently anyway.
03LLM fine-tuning & evaluation
Fine-tuning is worth it when a base model keeps missing your format, your vocabulary or your language.
04AI automation for business
Most automation fails for human reasons, not technical ones.
05Backend engineering
Users judge a product by its interface and abandon it because of its backend.
06AI training for teams
Adopting AI is mostly a people problem.
07Security-minded reviews
Security has been my long-running research interest: how systems get broken, and how often the way in is a convincing message rather than a clever exploit.