evidoria

← Back to browse

Good practice Imported

Jangat — Senegal's LLM-Powered Tool Let 19,000 Voters Compare Presidential Candidates' Programmes

Senegal · Dakar · See the Senegal profile · See the Dakar profile

Evidence: Descriptive / self-reported Top 89% 33/100 · Ask Evidence Copilot about this practice

A four-engineer Senegalese team built Jangat, an LLM-based app letting voters search and compare all 20 candidates' programmes by topic; it drew 11,000 connections in its first week and 19,000 in the campaign's final ten days before the March 2024 election.

11,000
Connections, first week (March 2024)
19,000
Users, final ten days of campaign (March 2024)
Jangat — Senegal's LLM-Powered Tool Let 19,000 Voters Compare Presidential Candidates' Programmes

Details

Maturity
Pilot
Promoter
Institut des Algorithmes du Sénégal (IAS)
Period
2024
Keywords
civic tech, elections, citizen engagement, LLM

Context

A four-person team at Senegal's Institut des Algorithmes built Jangat, an LLM-based tool letting voters search and compare all 20 candidates' programmes by topic, ahead of the March 2024 presidential election.

Results

The platform recorded 11,000 connections in its first week and about 19,000 in the campaign's final ten days; usage measures reach, not any evaluated effect on voter knowledge or turnout.

Implementation
Indicative cost
Low (< €50k)
Time to results
Short (< 1 year)
Staffing & skills
Institut des Algorithmes du Sénégal (four-person engineering team)

Conditions for success

  • extension to further elections/countries (discussed for Benin, Côte d'Ivoire) to demonstrate replicability

Do you run this practice? Claim it — verified implementers get a public contact pathway and can propose corrections.

Data sources

Where this practice's information was retrieved from, and when.

Attachments

Similar practices you may find useful