Skip to main content

Automatic production of summary notes for dossiers related to bills

Italy - Chamber of Deputies

Use case ID: 009

Author: IT Department, Chamber of Deputies of Italy

Date: 22 May 2024

Objective: 

Create notes for dossiers related to bills by using large language models (e.g. Llama 2).

Actors: 

  • Business units

Prerequisites:

  • Existing database of bills
  • Existing content management systems for bills

Scenario:

  1. The user selects a bill to be used as input.
  2. The AI model is executed on the input bill.
  3. The AI model returns informative notes regarding the input bills.
  4. The notes are proposed to the user.
  5. The user can evaluate the quality of the notes; the notes can be used as a support for producing parliamentary documentation.

Expected results:

  • User satisfaction in producing parliamentary documentation is improved.
  • It takes less time to produce parliamentary documentation.

Potential challenges:

  • Ensuring the AI tool provides accurate and relevant responses

Data requirements:

  • Existing database of bills
  • Existing content management systems for bills

Integrations with other systems:

  • Database of bills
  • Content management systems for bills
  • Software used by colleagues to produce parliamentary documentation

Success metrics:

  • User satisfaction scores
  • Reduction in the time needed to produce parliamentary documentation

 

The Use cases for AI in parliaments collection is published by the IPU’s Centre for Innovation in Parliament as part of the Parliamentary Data Science Hub’s project to create guidelines for AI governance in parliaments.

This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International licence. It may be freely shared and reused with acknowledgement of the author and the IPU. 

A use case describes how a system should work. It is used to plan, develop and measure implementation. A use case is not the same as a case study, which is a descriptive text of an actual project’s implementation. Please note that this use case is provided “as is” and neither the IPU nor the author accepts any responsibility for its use.

For more information about the IPU’s work on artificial intelligence, please visit www.ipu.org/AI or contact [email protected]