Type of work 04 of 06

Data and AI

AI agents

A software assistant that uses a large language model (LLM) to chain several steps across your tools and see a task through, within a scope you set.

Builds onData science

Illustration: a glowing brain marked “AI” surrounded by charts, a database and servers
Fig. 1

Definition

What it is

An agent is a program that uses a large language model (LLM) to choose what to do next and to call tools: read a document, query a database, draft a message. Because the model can get things wrong, the actions it is allowed, its limits and the points where a person signs off are part of the design.

Our work

What we do

The team defines with you the tasks the agent takes on, the tools it may call and what still needs your approval, then develops the agent and measures its results on representative cases. A record of its actions is kept so that you can review them.

During the free scoping call, we look with you at the task in view, the tools involved and what must still be approved by a person.

Deliverable

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.

What you receive at the end of the project, and at which step
DeliverableContentsHanded over at
DeliverableDocumented source codeContentsThe agent’s code in a repository, with its documentation: the tools it calls, its limits and its approval points.Handed over at05 · Close-out and support
DeliverableHandover sessionContentsA 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

Next step

Let’s talk about your project. The scoping call is free.

An initial conversation to understand your need, then a written quote: scope, deliverables, timeline, price.

Email the board

junior.eurecom.tech@gmail.com

  1. 01You describe what you need.
  2. 02We scope the project with you.
  3. 03You receive a written quote.