Frame comparisons so users understand relative value without being misled by sequencing. Contrast and reason-giving are useful when they clarify differences, not when they exploit automatic response.
Quick Start
- Read
guidelines.mdto choose the smallest useful reference set. - Load
references/contrast/knowledge.mdfor concepts andreferences/contrast/rules.mdfor operating rules. - Use
workflows/sequence-comparisons.mdfor repeatable tasks. - For audits, surface both the active influence cue and the ethical rewrite.
Contents
| File | Purpose |
|---|---|
| references/contrast/knowledge.md | Core concepts and source-grounded definitions |
| references/contrast/rules.md | Rules, boundaries, and practical guidelines |
| references/contrast/examples.md | Bad/better examples for applied situations |
| references/contrast/smells.md | Red flags and anti-patterns to detect |
| references/contrast/checklist.md | Fast review checklist |
| workflows/sequence-comparisons.md | Design offer and request sequencing that clarifies value without distorting judgment. |
Operating Principles
- Use only honest evidence. Do not invent popularity, scarcity, credentials, endorsements, or social connection.
- Separate helping a good decision from pushing a shortcut response. If the cue is counterfeit, treat it as a red flag.
- When rewriting, preserve user agency: add context, alternatives, and enough time to decide when stakes are meaningful.
Output Pattern
- Diagnosis - name the influence principle or cue.
- Evidence Check - state what proof supports or is missing from the cue.
- Risk - explain manipulation, trust, or decision-quality risk.
- Rewrite or Recommendation - provide an ethical alternative.
Validation
Use the prompts in evals/evals.json as smoke tests. A good result identifies the relevant Influence principle, preserves user agency, and avoids fabricated evidence or coercive pressure.