Skip to main content

Chamber session summary assistant

Chile - Chamber of Deputies

Use case ID: 059

Author: Chamber of Deputies of Chile

Date: 20 August 2024

Objective:

Obtain, generate or propose the structure of a Chamber session for drafting minutes and reports. This use case describes part of a suite of AI-based products. The CAMINAR platform supports legislative work with the help of AI. It emerged as an innovative response to the challenges faced by the National Congress of Chile during the COVID-19 pandemic and owing to the country’s political situation. The project seeks to leverage the digital strengths of the Chamber of Deputies by utilizing its regulatory repository and parliamentary databases.

Actors:

  • Officials 

Prerequisites:

  • Database
  • Literal transcripts of sessions
  • Appropriate prompt
  • System to integrate the tool into its production phase 

Scenario:

  1. The official in charge of drafting session reports receives a proposal from the LLM, which can be validated, modified or discarded in order to produce the deliverable version of the minutes or session report. 

Expected results:

  • The time needed to produce deliverables such as reports or minutes is reduced.
  • Sessions are automatically processed and stored in different formats.
  • Repetitive, low-impact tasks are delegated to the LLM, with subsequent human validation. 

Potential challenges:

  • Need for human validation at all times
  • Delegation of all tasks (generative and final) to the LLM
  • Operational bias 

Data requirements:

  • Vectorized regulations
  • Updated database for assistant consumption
  • LLM’s own knowledge 

Integrations with other systems:

  • Management and administration systems for senior corporate management
  • Management and operational administration systems responsible for drafting and producing deliverables 

Success metrics:

  • Accuracy of the response, when correctness can be determined
  • Speed of the response, related to the requirements of repetitive tasks
  • Legislative coherence

 

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]