Content risk classification engine

Data governance and semantic analysis

Designed and implemented an AI-driven classification system that analyzes internal content standards documentation and assigns priority levels (critical, high, medium, low) to individual sections. This system enables downstream AI writing tools to distinguish between rigid requirements and flexible guidance, improving both compliance and output quality.

At a glance

Goal

Enable AI-generated content to adhere to content standards with appropriate levels of strictness, balancing compliance with creative flexibility.

Challenges

·Ambiguity in content standards language and structure
·Lack of labeled training data
·Pressure to move faster
·Need to balance AI system needs and human user needs

Solution

Create a way to take a disparate set of standards and build in risk assessment that can be readable by both AI and humans.

Impact

·Reinforced regulatory requirements for non-writers
·Increased generation flexibility by allowing non-critical guidance to be applied more adaptively
·Established a foundation for AI governance by operationalizing policy into machine-readable logic

Process

Defined the priority framework

Established clear criteria for critical, high, medium and low classifications

Developed a semantic classification approach

Built system based on natural language processing to interpret meaning and intent in standards

Created a training and evaluation set

Generated labeled examples to bootstrap model performance, focusing on regulatory required language

Iterated on model collaboration

Tuned classification thresholds to strike the right balance between strict compliance and generative flexibility

Designed structured output for integration

Standardized outputs into a format consumable by AI writing systems, enabling dynamic enforcement of content rules during generation

What shipped

Delivered a scalable classification system that transforms static content standards into actionable inputs for AI systems, enabling more reliable and context-aware content generation.

Impact

→Reinforced regulatory requirements for non-writers
→Increased generation flexibility by allowing non-critical guidance to be applied more adaptively
→Established a foundation for AI governance by operationalizing policy into machine-readable logic

← Back to all work