competing-hypotheseslisted

# Analysis of Competing Hypotheses Don't pick the first plausible approach. Map the full solution space. Evaluate each against evidence. Find the one that best explains all the constraints. ## Core Principle The CIA developed ACH because analysts kept falling for confirmation bias -- finding evidence that supported their first hypothesis and ignoring the rest. The same happens in engineering. You think of an approach, find reasons it works, and stop looking. ACH forces you to consider ALL plausible approaches and evaluate them against ALL evidence. ## When to Use - Choosing between architectures, frameworks, or libraries - When "the obvious choice" hasn't been compared to alternatives - When team members disagree on approach - When the user needs counterpoints to their proposed solution - When a technology bet has limited reversibility ## The Process ### Step 1: List All Plausible Hypotheses Compare the genuinely credible approaches; 3-5 is a useful default, not a minimum. Two may be enough. Do not invent alternatives to fill a quota. Rules: - Each must be technically credible; cite real use when available and label unproven approaches rather than inventing production precedent. - Include the user's proposed approach - Look for a materially different option the user may not have considered; include it only if credible. - Consider "do nothing" or "simplest possible"; explain if constraints rule it out. ### Step 2: List All Evidence Gather evidence from all available