AI development
AI features that do a clear, checkable job.
Practical AI features built into your software or workflows, such as assistants that answer from your own documents.
What we do
- We design and build software features that use AI language models for a specific, agreed task, and we test them on examples you give us before anything goes live.
- We can add these features to software you already have, or build a small standalone tool around them.
- We tell you plainly where AI is a poor fit for a task and a simpler approach would work better.
Typical projects
General examples of the kind of work we take on. They are not descriptions of past clients.
- An assistant that answers questions from your own documents and shows where each answer came from.
- Pulling structured details out of documents you receive, such as forms or emails, for a person to check.
- Sorting and routing incoming messages or requests so they reach the right person faster.
- Drafting summaries or first replies that a member of your team reviews before they are sent.
- Adding an AI feature to an existing web application, with a way to switch it off.
Tech we use
- Language models from established providers through their business interfaces, or open models run on infrastructure you choose.
- Search over your own documents (retrieval), so answers are based on your content.
- TypeScript, Python, Node.js and PostgreSQL for the software around the model.
- Test sets built from your examples, so you can see how well a feature works before you rely on it.
Your data
- We never use your data to train AI or machine learning models without your written consent, and only for your own project.
- We agree with you which model provider is used and where your data goes before any data is sent to a model.
- Where a provider offers it, we use business settings that stop your data being used to train their models.
More on our Privacy Notice.
What we don’t do
- We don’t build AI that makes decisions about people on its own, such as hiring, credit or medical decisions.
- We don’t build tools for surveillance, identifying people from their face or voice, or imitating real people.
- We don’t promise that AI output is always correct. Every feature we build is designed for a person to check the results that matter.
- We don’t give financial, investment, legal, tax or medical advice, and we don’t provide any regulated financial service.
- We never hold, receive or move money on behalf of clients or their customers.
Every project must also follow our Acceptable Use Policy.
How we work
Every project follows the same steps: a scoping call, a written fixed-scope quote with the price, milestones you review, and a handover with the source code, documentation and access. Ownership of the source code passes to you once the agreed price is paid in full.
Support is available Monday to Friday, 09:00–17:30 (our time zone, UTC+4), except public holidays, with no out-of-hours or on-call service.
See how every project works, what you get and how we handle your data
Who does the work
Our services are delivered by qualified independent contractors, under the supervision of our board.
All work is delivered remotely, on a professional services basis.
We work with small and medium-sized businesses and individual professionals buying for their professional work. We serve customers worldwide, except where we’re incorporated.
How to start
Tell us about your project with our enquiry form and say you’re interested in AI development. Already a customer? Open a ticket instead.