Israel Election 2026 Vote Decision
Working out who to vote for in the 27 October 2026 Knesset election, starting from a voice note of my views
About This Project
This project implements a data-driven approach to electoral decision-making by converting a 42-minute voice note of political priorities into a structured rubric and scoring system. Using a combination of AI agents and data processing, the project evaluates all parties on the 2026 Knesset ballot against the user's specific policy preferences, including tenant protection, housing, and national governance. The workflow includes automated transcription, rigorous data analysis, and the generation of comprehensive PDF reports detailing the scoring methodology and final rankings.
Built using Typst for report generation, the project utilizes Claude Opus and Sonnet models to perform qualitative research and quantitative scoring on party lists. It incorporates polling data and candidate information to provide a transparent, reproducible analysis. The repository includes an accompanying interactive Hugging Face space that allows users to adjust weighting parameters to observe how individual priorities impact party rankings, offering a template for evidence-based voter research.