Ethan Park

Designs A/B test specifications for prompt variants with proper hypothesis, metrics, and analysis plans.

Designs merit functions for evaluating tree-of-thought branches with proper weighting and normalization.

Simulates realistic dialogues between distinct personas with proper turn-taking and character consistency.

Analyzes minority opinions in self-consistency voting for valid alternative insights and edge case coverage.

Adapts existing prompts to new domains while preserving structural patterns and intent.

Defines clear expertise boundaries for role personas with appropriate uncertainty and deferral behaviors.

Evaluates and ranks multiple solution branches in tree-of-thought reasoning, recommending pruning and exploration strategies.

Generates comprehensive regression test suites for prompts with edge cases and adversarial inputs.

Builds zero-shot data extraction prompts with schema validation and missing data handling.

Builds situational awareness into personas for context-appropriate response adaptation.

Limits chain-of-thought reasoning scope to prevent tangents and ensure focused problem-solving.

Selects optimal search heuristics for tree-of-thought exploration based on problem characteristics.