Data and AI
LLM integration
A large language model (LLM) connected to your tools or documents: we first assess what it brings to your case, then, where it makes sense, integrate it.
Builds onData science

What it is
A large language model (LLM) is an artificial intelligence model trained on large amounts of text, able to draft, summarise or answer questions. Its answers can be wrong: its value has to be measured on your case before any integration.
What we do
The team first assesses, on examples that reflect how you would use it, what the model brings. Where it makes sense, the team connects it to your tools or documents. Depending on the quote, the project ends with the integration’s source code or with a study report.
During the free scoping call, we look with you at the intended use, the documents involved and their constraints.
What you receive
The deliverable is defined in the quote. You receive it at the close-out step, and a handover session then closes the project.
| Deliverable | Contents | Handed over at |
|---|---|---|
| DeliverableSource code | ContentsThe integration’s code in a repository, with its documentation, if the project includes development. | Handed over at05 · Close-out and support |
| DeliverableStudy report | ContentsThe assessment carried out, its results and its conclusions, if the project is a study. | Handed over at05 · Close-out and support |
| DeliverableHandover session | ContentsA session to hand over the deliverable, walk you through how it works and its documentation, and answer your questions. | Handed over at05 · Close-out and support |
Same area
- 01ModelsModels trained on your data, to forecast, classify or analyse.
- 02Data pipelinesThe pipeline that collects, cleans and serves your data.
- 04AI agentsAn assistant that chains steps across your tools, under your control.
- 05AutomationRepetitive tasks handed over to a program.
- 06AI advice and scopingWhether AI helps your case, and where to start.