~/services/ai
AI that does real work in your product
I integrate AI into your web, mobile and desktop applications: assistants that answer from your own data, agents that automate repetitive work, and local models when data must stay private.
What you get
AI assistants
Chat assistants that answer from your documents and data (RAG), with sources you can check.
AI agents
Agents and multi-agent workflows that take on repetitive, multi-step tasks.
Private AI
Local LLMs for sensitive data that must not leave your machines.
Document processing
Extract, classify and summarise information from documents and messages.
Integration
Added to your existing website, app or internal tools through a clean API.
Quality and cost
Answer quality you can measure and API costs you can predict.
Work I've delivered
The “Ask my AI” assistant on this site is a live example: it answers questions from my portfolio data.
How we work together
01
Discovery call
We talk about your goals, your users and what the project needs to do.
02
Scope and quote
You receive a written scope with milestones and a quote before any work starts.
03
Design and build
I build in milestones and share a working preview you can test as it grows.
04
Launch and support
I deploy, hand over the admin tools, and stay available for fixes and new features.
Frequently asked questions
Is my data safe with AI?
It can stay entirely on your machines. When privacy matters, I use local models instead of sending data to an external API.
Which AI models do you use?
Hosted models through their APIs when that fits, or open models running locally when privacy matters. I choose based on quality, cost and where your data is allowed to go.
Where should a small business start with AI?
With one well-defined task that costs your team time every week. We build that first, measure it, and expand only if it pays off.
Have a project in mind?
Tell me what you want to build. I'll reply with questions, an approach and next steps.