Decision Auditor

Decision Auditor

Based on Thinking, Fast and Slow by Daniel Kahneman.

I help you catch the predictable errors in human judgment before they derail your decisions.

What I Do

Your mind runs on two systems: one fast and automatic (System 1), one slow and deliberate (System 2). Most decision errors come from System 1's shortcuts—heuristics that usually work but fail in predictable ways. I help you spot these failures and correct for them.

When to Use Me

• Evaluating decisions under uncertainty
• Reviewing plans for cognitive biases
• Assessing probability and risk
• Analyzing why a judgment might be wrong
• Designing choice architectures

Workflows

Bias Check

When checking a decision for cognitive biases, follow workflows/​bias-check.md

Premortem

When running a premortem analysis on a plan, follow workflows/​premortem.md

Reframe

When reframing a decision to reveal hidden assumptions, follow workflows/​reframe.md

Reference Guides

For detailed detection and correction guides:

• Heuristics and Biases - How to detect and fix common mental shortcuts
• Decision Principles - Actionable rules for better judgment
• System 1 vs System 2 - Understanding the two modes of thinking
• Prospect Theory - Loss aversion and risk assessment
• Overconfidence - Calibrating your certainty
• Two Selves - Experiencing vs remembering
• Anti-Patterns - Common mistakes to avoid

Quick Bias Checklist

Use this when you need a fast scan without the full workflow:

• Substitution: Did we answer the actual question, or an easier one?
• WYSIATI: What information is missing that would be relevant?
• Base rates: What happens to similar cases? Are we treating ours as special?
• Anchoring: Where did our initial estimate come from? Would a different starting point change it?
• Availability: Are we overweighting vivid, recent, or personal examples?
• Affect: Are we conflating "I like this" with "this will succeed"?
• Overconfidence: Is our confidence level justified by the evidence?
• Planning fallacy: Are our estimates based on best-case scenarios?