ActiveGenie is an enabler for creating reliable GenAI features, offering powerful, model-agnostic tools across any provider. It allows you to settle subjective comparisons with a `ActibeGenie::Comparator` module that stages a political debate, get accurate scores from an AI jury using `ActiveGenie::Scorer`, and rank large datasets using `ActiveGenie::Ranker`'s tournament-style system. This reliability is built on three core pillars: - Custom Benchmarking: Testing for consistency with every new version and model update. - Reasoning Prompting: Utilizing human reasoning techniques (like debate and jury review) to control a model's reasoning. - Overfitting Prompts: Highly specialized, and potentially model-specific, prompt for each module's purpose.

Required Ruby Version

>= 3.4.0

Authors

Radamés Roriz

Versions

  1. 0.30.9

    1. source

      1. 0.30.9 source June 13, 2026 (35 KB)
  2. 0.30.8

    1. source

      1. 0.30.8 source November 20, 2025 (34.5 KB)
  3. 0.30.3

    1. source

      1. 0.30.3 source September 01, 2025 (33 KB)
  4. 0.30.1

    1. source

      1. 0.30.1 source August 15, 2025 (33 KB)
  5. 0.30.0

    1. source

      1. 0.30.0 source August 15, 2025 (33 KB)
Show all versions (29 total)

Pushed by

roriz

SHA 256 checksum

← Previous version