Skip to content
DAVA

LLM features · Retrieval · Model selection

AI engineering and LLM feature development

We build features powered by large language models (LLMs) into apps and sites: answers drawn from your own content, structured output that is checked before other code uses it and a server-side proxy that keeps your API keys out of the browser. We choose the model for the task, not for the latest announcement. We build our own products this way.

What we do

From a prompt to a feature you can ship.

LLM features

Chat, drafting, summarising, extraction and classification built into an app or site, with output checked against a schema before the rest of the code uses it.

Answers from your own content

Search over your own documents using embeddings (pgvector, hybrid search and reranking), so answers point back to the documents the model was given.

A server-side proxy

The model is called from your server or an edge function, never the browser, so API keys never reach it and every request can be checked, rate-limited and logged.

Guardrails

Mitigations for prompt injection and for wrong or invented answers, plus pre-written replies for input categories you define, so a feature declines rather than guesses when it is out of its depth.

Model selection

The hosted or open-weight model picked per task on cost, quality and where the data is processed. We can explain the choice and change it later.

Agents and automation

Where a single call is not enough: tool use, multi-step agents and workflows, scoped to one job and evaluated against it before release.

  • LLM
  • Claude
  • OpenAI
  • Open-weight models
  • RAG
  • pgvector
  • TypeScript
  • Cloudflare Workers

Proof

This is our own work, not client projects.

  • Our own AI product, in developmentWe are building a product with AI at its core. It is not released yet; we will show it when it launches.
  • Our own agent systemWe built and maintain a knowledge base of AI agents and automated workflows, and use it daily to do this kind of work.
  • Sourced adviceFor each model or technique we recommend, we record a source and the date we read it, so the advice can be checked and kept current.

Questions

Questions about AI engineering

Have you built AI features for clients?

Not yet. AI is newer for us than our commerce work. We are building our own AI product and use AI agents daily in our own work. We would bring the same tested, measured method to client work.

Which models do you use?

Whichever fits the task. We compare Anthropic's Claude, OpenAI's models and open-weight models on cost, quality and where the data is processed, and we keep the choice easy to change.

Where does our data go?

We tell you before we build. Vendors differ on whether they process data in the EU and on whether they keep or train on it; for sensitive cases we can look at open-weight or self-hosted options.

Is this just using AI to write code?

No. We do build with AI-assisted tooling, but this service is about putting AI features into your product: the model, the retrieval, the proxy and the guardrails that ship with it.

Start a project

Tell us what you are building.

We reply with questions, a rough plan and an honest view of the effort.

Start a project