Finding Stories in the Talmud

Using AI to identify narrative passages in the Babylonian Talmud

Talmud Text
AI Analysis
Identified Stories

Why This Matters

The Babylonian Talmud is filled with stories—narratives about rabbis, their lives, their teachings, and the world around them. These stories are woven throughout the Talmud's legal discussions and are treasures of Jewish literature.

But there's a problem: these stories are scattered throughout the Talmud with no index. They appear without warning between legal debates, sometimes just a few sentences, sometimes spanning pages. Scholars spend years learning to recognize them.

Our Goal: Create the first comprehensive catalog of narrative stories in the Talmud, making them accessible to scholars, students, and curious readers everywhere.

The Challenge

Finding stories in the Talmud isn't a simple search problem. Here's why:

🔍

No Clear Markers

Stories don't announce themselves. The same Hebrew words appear in both legal and narrative contexts.

📏

Variable Length

Stories range from two sentences to multiple pages, with no standard format.

⚖️

Mixed Content

Narratives are interwoven with legal discussions, often mid-paragraph.

Current Progress

We're starting with Tractate Ketubot and expanding from there.

222
Pages Analyzed
172
Stories Found
96.3%
Accuracy (Pages 61-112)
1
Full Tractate

The Journey: 50% to 92%

Each round of expert feedback transformed the system. What started with a 50% false positive rate became a 96.3% accurate pipeline—through eight versions of learning what makes a story.

50%
v4.1
First expert review
86%
v5.1
128-passage review
92.1%
v7
Gemini 3 Flash
96.3%
v8
Cross-page fix

The biggest breakthrough came from expert validation. When Talmud scholar Jeffrey Rubenstein reviewed our first results, he found the AI was confusing legal attribution ("Rabbi X quotes Rabbi Y") with characters in a story. That single insight eliminated 53 false positives. Every version since has been shaped by his corrections.

Learn More

Project Team

Jeffrey L. Rubenstein, Ph.D.

Scholarship & Validation
  • Skirball Professor of Talmud and Rabbinic Literature, New York University
  • One of the world's leading experts on Talmudic narratives
  • His scholarship directly informs our detection criteria

Selected Works

  • Talmudic Stories: Narrative Art, Composition, and Culture (1999)
  • The Culture of the Babylonian Talmud (2003)
  • Stories of the Babylonian Talmud (2010)
  • Rabbinic Stories (2002)

Simon B.

Technical Development
  • Not a software engineer, but plays one on TV (with Claude Code as co-star)
  • Brought the curiosity; AI brought the code
  • Proof that you don't need a CS degree to build something meaningful—just good questions and persistent debugging

Powered By

Sefaria
Text data from the free library of Jewish texts
sefaria.org
Google Gemini
AI classification engine
ai.google.dev
Anthropic Claude Code
Development assistant
claude.ai