Skip to content
How to ThinkIn the Age of AI

The competent stranger test

Test specification completeness by asking whether a competent stranger with relevant skills but zero context could produce an acceptable result from your specification alone—if not, the missing information must be externalized before delegation.

When This Fires

  • Before delegating any significant task — apply the test to your specification
  • When delegation produces disappointing results despite the delegate being competent — the spec may be incomplete
  • When writing delegation briefs, project descriptions, or task assignments
  • Complements Three-component handoff spec (three-component handoffs) with the specification completeness test

Common Failure Mode

Assuming shared context: "They know what I mean." They don't — or they know 60% of what you mean and fill in the remaining 40% with their own assumptions. The resulting output is 60% what you wanted and 40% surprise, producing rework that consumes more time than writing a complete specification would have.

The Protocol

(1) Write your delegation specification. (2) Imagine a competent stranger reading it: someone with relevant technical skills but zero context about you, your project, your preferences, or your organization. (3) For each decision the stranger would need to make: is the answer in the specification? If yes → the spec covers this. If no → the stranger will guess, and their guess may not match your expectation. (4) For each gap, externalize the missing context into the specification: quality standards, tone preferences, deadline interpretations, scope boundaries, success criteria. (5) Re-test: with the added context, could the stranger now produce an acceptable result? If gaps remain → continue externalizing. (6) The specification is complete when the competent stranger needs to ask zero clarifying questions.