Analysis of Competing Hypotheses (ACH)

ACH builds an evidence-by-hypothesis matrix, scores each item of evidence for how well it disconfirms each hypothesis, and favors the hypothesis with the least inconsistent evidence. It is a famous intelligence-analysis technique, and it was tested and found wanting: in randomized controlled studies it raised participants' confidence without improving accuracy, and showed no debiasing or judgment-quality gain. This skill therefore does not reproduce the matrix as if it were valid. It owns the request, leads with what the controlled evidence shows, and routes you to the evidence-based move your actual job needs. The output is an honest redirect brief, not a disconfirmation matrix with a declared winner.

Before you run this: what the controlled evidence shows

ACH is tier X (tested and found wanting, not merely undertested). On its own home population and stated purpose, the controlled record is null-to-negative:

• Otzipka (2025, Applied Cognitive Psychology): applying ACH significantly raised participants' confidence with no accuracy gain (confidence without accuracy).
• Dhami, Belton and Mandel (2019, Applied Cognitive Psychology): 50 intelligence analysts randomized; steps were skipped, bias effects were mixed, and ACH may have increased judgment inconsistency and error.
• Karvetski and Mandel (2020, Judgment and Decision Making, N=227): no gain in additivity, coherence, or consistency, and slightly reduced reliability.
• Whitesmith (2019); Maegherman et al. (2021); Dhami et al. (2024, the matrix layout specifically failed to reduce bias); Otzipka and Volbert (2026): no debiasing.

The mechanism's documented flaw: counting inconsistencies treats evidence items as independent and equally weighted, which they almost never are. Institutional adoption is not outcome evidence. So this skill will not hand you a filled matrix and a "least-inconsistent" verdict, because that artifact is exactly what the trials condemned. It states the caveat and redirects.

When to Use

• The user asks for ACH (or a "competing hypotheses matrix") by name, and an honest warning plus a redirect serves them better than silently building the discredited artifact or refusing outright.