evidoria

← Back to browse

Good practice Imported

Sor Juana — Mexico's Supreme Court AI Chatbot for Understanding Draft Rulings

Mexico · Mexico City · See the Mexico profile · See the Mexico City profile

Evidence: Descriptive / self-reported Top 97% 20/100 · Ask Evidence Copilot about this practice

Mexico's Supreme Court launched Sor Juana, an AI chatbot answering plain-language questions about one minister's draft rulings — but it remains a single-office pilot with no published usage or accuracy results.

Sor Juana — Mexico's Supreme Court AI Chatbot for Understanding Draft Rulings

Details

Maturity
Pilot
Promoter
Suprema Corte de Justicia de la Nación (SCJN)
Period
2026 (pilot, ongoing)
Keywords
judiciary, courts, legal technology, public-sector AI

Context

Mexico's Supreme Court of Justice of the Nation (SCJN) sought a way to help the public understand draft rulings currently being voted on by the Court, which are otherwise written in technical legal language.

Objectives

To let any member of the public enter a docket number and ask plain-language questions about a draft judgment.

Activities

Minister Ana Margarita Ríos Farjat's office introduced the chatbot Sor Juana (named for Sor Juana Inés de la Cruz), built using Streamlit, Google's AI tools and the Pinecone vector database, covering only draft rulings supervised by that minister's office rather than the Court's full docket.

Results

The tool is live and answering public queries, but no usage volumes, accuracy rates or user-satisfaction figures have been published; independent trackers such as CIDE's Algoritmos Públicos and Universidad de los Andes' algorithm registry list it as an unevaluated public-sector AI system to watch.

Conclusions

Sor Juana remains a single-office pilot with no demonstrated replication to other SCJN dockets or courts, and no published accuracy or bias assessment.

Implementation

Indicative cost
Low (< €50k)
Time to results
Short (< 1 year)

Commonly funded by

National / regional programmes

Indicative funding routes for practices of this type — always check each programme's current calls and eligibility rules.

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