Testimonial: a look back at the deployment of INSA Lyon's AI chatbot

March 31, 2026 Pauline Zucca 4-minute read

INSA Lyon, a prestigious engineering school, partnered with Wikit to deploy a chatbot powered by generative AI on its website for prospective students: www.rejoindreinsalyon.com. Ophélie Tambuzzo, Director of Communications, discusses the implementation of this chatbot and its benefits.

Could you give us a brief overview of INSA Lyon?

For over 60 years, the Institut National des Sciences Appliquées de Lyon has been training humanist engineers to meet the socio-ecological and digital challenges of a changing world. Each year, INSA Lyon welcomes over 6,000 students and 600 PhD students, and graduates over 1,000 engineers and 150 PhDs. As a reference center, the school is also developing excellent, responsible and supportive research, based on 22 laboratories. INSA Lyon is part of the INSA Group, the leading network of French public engineering schools, which currently comprises 7 establishments and 6 partner schools in France.

What issue(s) did you hope to address by implementing a chatbot?

As part of the expansion of our website, www.rejoindreinsalyon.com, we were looking for solutions to improve the experience of high school and university students wishing to join us, and to enable interactivity with this target group.

The chatbot was one of them, facilitating access to the wealth of information available on the site and offering a new response channel to the many requests we receive, particularly during the opening period of the Parcoursup platform. Another advantage is that the chatbot offers a fun, differentiating experience for our main target of high school students.

Why did you choose Wikit?

Our tight schedule for implementing the tool meant that we had to quickly rule out solutions based on conversational trees, which would have required a heavy investment on the part of INSA. Generative AI seemed a good compromise.

After reviewing several proposals, we chose Wikit for several reasons: the proposal’s alignment with our requirements, adherence to the schedule, support during implementation, cost, and geographical proximity.

What were the steps involved in deploying your chatbot?

We began by defining the scope and customization elements of the chatbot, both in terms of text and graphics. Next came the “test run” phase, with the goal of creating at least 50 questions, each with its source and the expected answer. We worked in iterations togradually refine the chatbot’s responses. This took some time, and adjustments were necessary. Since INSA Lyon is part of a group of schools, some responses did not apply to our institution. This allowed usto identify which data sources needed to be removed from the scope.

Finally came the pre-production acceptance phase before going live.

We met weekly to check on the progress of the project, discuss any difficulties encountered and find solutions. The project ran from mid-November to the end of January.

In your opinion, what is the main benefit of generative AI for chatbots?

The main benefit of using generative AI for chatbots lies in their ease of implementation. AI is capable of processing very large amounts of data automatically, enabling rapid deployment with 24/7 availability.

Be careful, however, to remain vigilant and regularly monitor conversations to identify unanswered questions or incorrect answers.

The introduction of a "reflex sheet" provides a quick and effective solution to recurring questions and/or questions that are not satisfactorily answered.

What benefits have you seen since implementing the chatbot?

Our team was able to see for themselves just how useful the tool can be at an event. When we organized the school's Discovery Day on Saturday, February 3, it was important to ensure that everything was clear about the day's program, especially as we had both face-to-face and distance learning registrants. The chatbot was thus able to answer practical questions about registration, access, conferences and replays , and significantly reduced the number of requests we would have received by e-mail or telephone.

Don't miss our next resources

Our other resources

Are you ready to harness the potential of AI?

Dive into the Wikit Semantics platform and discover the potential of generative AI for your organization!

Request a demo
chatbot INSA