Bill drafting assistant

Bill drafting and amendments

Chile - Chamber of Deputies

Use case ID: 048

Author: Chamber of Deputies of Chile

Date: 20 August 2024

Objective: 

Foster the integral and efficient creation of bills through the integration of multiple AI-based assistants, achieving analysis of quorum rating, admissibility, related norms and regulatory impact, among others.       

 

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:

  • Parliamentarians

Prerequisites:

  • XML database
  • Literal transcripts of sessions
  • Appropriate prompts
  • System to integrate the tool into its production phase

Scenario:

  1. The parliamentarian accesses a platform that, through the integration of all legislative area assistants, allows for the generation and analysis of a new bill, enabling admissibility, quorum rating, related norms and possible improvements to be determined.

Expected results:

  • The time required to produce and analyse bills is reduced.
  • Comprehensive, relevant and coherent bills are obtained, and these bills align with the stated objectives.
  • The contextual background, implications and side effects of the analysed bill are obtained.

Potential challenges: 

  • Integrity of the response and legal precision 
  • Bias limitations
  • Mis-interpreted response because the tool does not understand the context of relevant laws
  • Corporate responsibility exemption, ensuring the information provided is fully informative 
  • Need for human validation at all times
  • Use of the tool for unintended purposes
  • Blaming of the tool for the content it generates
  • Excess or contradiction of biases
  • Delegation of task completeness to the LLM

Data requirements:

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

Integrations with other systems:

  • Systems for creating, manipulating, storing or generating legal texts to achieve the defined objective in this use case 

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].