ai-output-critical-audit-designer

What problem does it solve?

It solves the problem of students being misled by confident, fluent AI text by replacing intuitive judgment with a structured protocol to evaluate AI output against Ennis’s six critical thinking standards.

Core Features & Use Cases

• AI-specific audit protocol: Generates a step-by-step method students can apply to detect AI characteristic failure modes (e.g., overconfident uncertainty-free claims, fabricated precision, shallow depth).
• Annotation system for close reading: Produces marking codes so students can identify failure types as they read the AI output.
• Rubric and push-back prompts: Provides Weak/Moderate/Strong descriptors aligned to clarity, accuracy, precision, relevance, depth, and breadth, plus sentence stems that help students challenge AI statements.
• Teacher modelling script: Includes a think-aloud example showing how an expert auditor applies the standards while explicitly decoupling fluency from reliability.

Quick Start

Use the ai-output-critical-audit-designer to generate an audit and annotation protocol for the AI-generated text about a given subject, at the specified student level, and against the selected Ennis standards.