Demos hide the failure cases
A feature that works on ten handpicked examples fails in public on the eleventh.
AI & automation
Add AI to your product that works on a Tuesday, not just in the demo.
We build AI features into your app or platform with evaluation sets, guardrails and cost limits, so they stay accurate, safe and affordable after launch.
- From
- £2,400
- Timeline
- 4–6 weeks
- You own
- The code, from day one
OpenAI Anthropic Claude Google Gemini Open models Vector search Python TypeScript n8n Zapier Make PostgreSQL REST APIs
This is for you if
- You run a software product and your customers are asking for AI features.
- You have a working prototype that is impressive but unreliable.
- You need to control cost, privacy and quality, not just ship a demo.
What it costs you now
What the problem really costs.
Costs scale with usage
Model calls cost money on every use. Without limits, success can be more expensive than failure.
Provider lock-in
Building directly around one vendor’s quirks makes the next price change or outage a crisis.
How it works
How we build it, step by step.
Four stages, each with something you can see and approve before we move on.
-
Define success as tests
Before building, we write the evaluation set: real inputs and what a good output looks like. It becomes your regression suite.
-
Pick the model on evidence
We compare candidate models on your tests for accuracy, speed and cost, and show you the trade-offs.
-
Build guardrails and fallbacks
Input and output checks, timeouts, retries and a graceful fallback so a failure never breaks the product.
-
Ship with cost and quality monitoring
Usage caps, cost dashboards and quality sampling so you see problems before customers do.
What you walk away with
Everything is yours.
Source files, documentation, accounts and keys transfer to you. Ongoing support is a choice, never a dependency.
- An evaluation test set
- Model comparison report
- Production integration with guardrails
- Cost caps and monitoring
- Provider-agnostic architecture
- Documentation and handover
Best fit
Works especially well for.
Straight answers
LLM and AI product features: your questions, answered.
Which models do you use?
We choose per task: the major hosted models from several providers, and open models where privacy or cost demands it. The choice is driven by your tests, not preference.
How do you handle sensitive data?
We minimise what is sent, choose providers with suitable data terms, and can run models in your own cloud account when required.
Can you improve an AI feature we already built?
Yes. Often the fastest win is adding an evaluation set and guardrails to what exists, then fixing what the tests expose.
What does it cost to run?
We estimate cost per use from real tests and set a ceiling, so you know the monthly range before launch.
Often paired with
More from this area.
-
Knowledge-base copilot
An assistant that answers staff questions from your own documents, with sources, so nobody has to ask the same person twice.
from £1,900 -
Web apps and SaaS
Custom web applications and subscription products, built to your business logic and your roadmap.
from £4,900 -
MVP builds
A focused six-to-eight-week programme that takes a product idea to a real, testable first version.
from £3,900
Start here
Want LLM and AI product features? See it before you pay.
Describe it in your own words. A person reads it, and for most projects you get a free mockup within one working day.