index / shloktilokani/TicketLens_Jev_vs_LLM
TicketLens_Jev_vs_LLM
Local-first app for classifying fictional ShopKart support tickets with TypeSafe Jev and an OpenAI GPT model, side by side. Compares both on category, subcategory, priority, sentiment and escalation, logs every run with token usage and cost, and measures accuracy on a labelled synthetic dataset. React + FastAPI + MongoDB.
Research and EvalsExtractionListedPython
Repository
Stars0
LanguagePython
License—
Created2026-11-07
Last pushed2026-11-07
Officialno
Judgment
Genuine Jev project0.82
gate 0.5
Uses Jev at runtime0.61
Is a meta list0.03
Is a reimplementation0.07
Quality scales
Substance1.48 / 3
gate 0.5
Docs2.36 / 3
Novelty1.42 / 3
Composite score0.56
Category distribution
Research and Evals0.67
Applications0.33
SDKs and Clients0.00
Integrations0.00
Agent and Dev Tooling0.00
Games and Simulation0.00
Learning0.00
Other0.00
Assigned categoryResearch and Evals
Category probability0.67
Category confidence0.62
PatternExtraction
Pattern confidence0.83
Curation
StatusListed
Reasongate passed
README pickno
Overridenone
Sources
- search:jev in:name,description,readme created:2026-11-07
Provenance
Modeljev-1.14.0
Question setv2
Judged at2026-11-07 12:20 UTC