Introducing Curebot Assistant

Knowledge. Answers. Inspirations.
Optimize the value of your resources with AI.

Our Curebot Assistant's vision

Interpret diversity and creativity in each result!

Our aim is to make monitoring, analysis and decision-making more effective and accessible to everyone. We are shifting gears in that direction. Curebot Assistant is built on a self-hosted Open Source LLM model that allows you to harness the knowledge hidden in information.

We are committed to offering transparency and flexibility to our users in their use and adoption of Curebot Assistant. You'll know exactly where to start when it comes to discovering new insights, carrying out your analysis step-by-step, and determining what actions to take.

We're committed to transparency and flexibility as you use and adopt Curebot Assistant.

A trust generative AI.

Our LLM model is self-hosted on our secure and private servers.

We designed Curebot with high standards of security and confidentiality. The development of our AI technologies confirms this commitment. Our self-hosted professional architecture guarantees the permanent protection of our customers' data while offering to exploit the power of AI.

Do you have any questions?
Curebot Assistant answers you.

Ask Curebot Assistant.

Enter any instructions you want to get the answers you need. Just ask.

Analyze resources.

Experience the potential of AI to support analysis and exercise a critical eye on information.

Summarize and syntheses.

Discover key takeaways in seconds to test new hypotheses.

Extract data.

Interpret information to help you make the best decisions.

Streaming responses.

Get instant insights making the monitoring experience more dynamic and personalized.

Prompt library.

Choose from a library of prompts specially designed by watch experts.

Contact us to test Curebot Assistant.

Research and development.

Several months of R&D were used to test different use cases, calculate quantitative statistics (response time, stability, performance...) and deconstruct qualitative data (linguistic, semantic, lexical, syntactic relevance, formatting, omission, hallucination...) with a human annotation campaign, blind, by multi annotators.

To frame our analysis and study the various constraints, we designed an experimental protocol. The aim being to compare and differentiate various LLMs both proprietary and OpenSource, but also several infrastructures, several hosting providers, several backend technologies... As part of this protocol, we tested the combination of all these criteria to obtain results that were as exhaustive as possible. In this way, we gathered valuable data on the relative performance of each combination, helping us to make informed choices in developing Curebot Assistant.

The diversity and richness of the experiments led us to objectively choose the best solution for implementing LLM on a self-hosted infrastructure, and thus meet our customers' needs for implementing these generative artificial intelligence technologies within our intelligence platform.

What does the future hold?

Curebot Assistant is just getting started. We're dreaming and working every day on developing new features! We continue to research and explore how AI can be harnessed to help our customers improve their intelligence and analytics experience.

The rest to come soon...