Case Study

Cassandre

Cassandre

An LLM-assistant for HR services of the French Ministry of Education

An LLM-assistant for HR services of the French Ministry of Education

THE FRENCH MINISTRY OF EDUCATION, IN COLLABORATION WITH THE FOUNDING TEAM OF PLEIAS, HAS INITIATED THE CREATION OF CASSANDRE, A LLM-BASED ASSISTANT DESIGNED TO STREAMLINE HR SERVICES WITHIN THE ACADÉMIE DE LYON. 

THE FRENCH MINISTRY OF EDUCATION, IN COLLABORATION WITH THE FOUNDING TEAM OF PLEIAS, HAS INITIATED THE CREATION OF CASSANDRE, A LLM-BASED ASSISTANT DESIGNED TO STREAMLINE HR SERVICES WITHIN THE ACADÉMIE DE LYON. 

This project focuses on introducing a knowledge assistant to help HR teams to navigate the intricate regulations and documentation that govern the varied personnel types within the education sector, and bring appropriate answers to their queries.

This project focuses on introducing a knowledge assistant to help HR teams to navigate the intricate regulations and documentation that govern the varied personnel types within the education sector, and bring appropriate answers to their queries.

Objectives

Complex Administrative Documentation Navigation:

text

Cassandre is tailored to interpret and provide guidance on the multifaceted rules and documentation specific to different personnel categories within the Ministry of Education.

Complex Administrative Documentation Navigation:

text

Cassandre is tailored to interpret and provide guidance on the multifaceted rules and documentation specific to different personnel categories within the Ministry of Education.

Accuracy and Factuality:

text

Ensuring that responses are not only rapid but also precise and grounded in factual information is a primary goal.

Accuracy and Factuality:

text

Ensuring that responses are not only rapid but also precise and grounded in factual information is a primary goal.

Rapidity and Comprehensiveness:

text

The tool aims to deliver comprehensive support operating much faster than manual or even embeddings-based research, improving the overall efficiency of HR services.

Rapidity and Comprehensiveness:

text

The tool aims to deliver comprehensive support operating much faster than manual or even embeddings-based research, improving the overall efficiency of HR services.

Challenges and Solutions

Complex Unstructured and Semi-Structured Documentation in Multiple Formats (pdf, text, images):

text

The diverse and complex nature of HR documentation within the Ministry of Education posed a significant challenge.

Complex Unstructured and Semi-Structured Documentation in Multiple Formats (pdf, text, images):

text

The diverse and complex nature of HR documentation within the Ministry of Education posed a significant challenge.

Ensuring Explainability:

text

To maintain the trust and confidence of HR agents, it is crucial to develop a system that not only provides accurate answers but also explains the reasoning and provides references leading to them.

Ensuring Explainability:

text

To maintain the trust and confidence of HR agents, it is crucial to develop a system that not only provides accurate answers but also explains the reasoning and provides references leading to them.

Training and Adaptation:

text

Recognizing the importance of effective interaction between HR agents and the AI, tailored training programs were implemented to familiarize users with Cassandre's capabilities and optimize its usage in daily operations.

Training and Adaptation:

text

Recognizing the importance of effective interaction between HR agents and the AI, tailored training programs were implemented to familiarize users with Cassandre's capabilities and optimize its usage in daily operations.

Technology and Methodology

text

Cassandre is a fine-tuned open weights (Mistral OpenHermès 7b) model which utilizes an interpretable Retrieval-Augmented Generation (RAG) infrastructure, integrating Knowledge Graph retrieval to enhance its ability to provide accurate and contextual answers.

text

Cassandre is a fine-tuned open weights (Mistral OpenHermès 7b) model which utilizes an interpretable Retrieval-Augmented Generation (RAG) infrastructure, integrating Knowledge Graph retrieval to enhance its ability to provide accurate and contextual answers.

text

The use of Knowledge Graphs which were processed and generated fully with pleias’ custom LLM largely improves the relevancy and precision of Cassandre’s responses, specifically in the cases where small employee groups with specific conditions are concerned.

text

The use of Knowledge Graphs which were processed and generated fully with pleias’ custom LLM largely improves the relevancy and precision of Cassandre’s responses, specifically in the cases where small employee groups with specific conditions are concerned.

CONTACT@PLEIAS.FR

CONTACT US

CONTACT@PLEIAS.FR

CONTACT US