Distribution of demands from MPs among groups of lawmaking experts

Bill drafting and amendments

Brazil - Chamber of Deputies

Use case ID: 019

Author: Chamber of Deputies of Brazil

Date: 14 June 2024

Objective:

Read the text of demands sent by MPs to the Legislative Consultancy Department for new bill drafting or research to support new bills, interpret this text, and suggest up to three groups of lawmaking experts who could handle the demand.

Actors:

  • MPs submitting demands
  • Legislative Consultancy Department experts (lawmaking experts)
  • Legislative Consultancy Department staff
  • AI system for screening and distributing demands from MPs

Prerequisites:

  • Demand distribution rules
  • Trained AI model for demand classification
  • Integration with digital services commonly used by MPs and legislative consultants

Scenario:

  1. When an MP wants a bill drafting or needs research to support a new bill, they send a demand to the Legislative Consultancy Department, which comprises a fixed number of groups of lawmaking experts.
  2. The AI model semantically analyses the demand and, according to the blend of its themes and approaches, suggests up to three groups of lawmaking experts that have a high probability of being appropriately skilled to handle the task.
  3. A Legislative Consultancy Department staff member checks the AI-generated suggestions and authorizes the demand to be distributed.
  4. A lawmaking expert handles the demand after it is distributed to their group.

Alternate flows:

  • When one of the AI model’s suggestions is greater than 90%, the demand will be distributed automatically.

Expected results:

  • The process of distributing demands among consultancy groups is more efficient.
  • Bias in the distribution of demands is reduced.
  • Workload for Legislative Consultancy Department staff is reduced.

Potential challenges:

  • Ensuring the AI model provides accurate responses
  • Monitoring changes in demand distribution rules
  • Monitoring changes in the lawmaking groups

Data requirements:

  • Historical demand distribution data for AI model training
  • Periodic verification of AI ​​model accuracy

Integrations with other systems:

  • Digital services commonly used by MPs and legislative consultants
  • Analytics and reporting tools

Success metrics:

  • Percentage of demands correctly classified by the AI model (Top-1 accuracy)

 

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].