// QUESTION CLASS

Is this claim defensible, and under which alternative hypothesis does it break?

Argumentative is the only engine that is not a report product. It is a method — Analysis of Competing Hypotheses (ACH), plus allied Structured Analytic Techniques — that runs inside every other engine's pipeline. When a Foundational report asserts a structural fact, Argumentative tests the strength of the evidence behind it. When an Anticipatory report assigns a confidence level, Argumentative interrogates the reasoning. When an Actionable report identifies a critical node, Argumentative stress-tests whether the claim survives the most damaging alternative interpretation. Argumentative can also be invoked standalone: "Here is a claim; here is the evidence; tell me whether the claim survives pressure." In that mode, it produces a short report showing the hypothesis matrix, the evidence weighting, the inconsistency count per hypothesis, and the surviving hypothesis (if any). This is the engine that exists to answer the question "are you sure?"

Argumentative

"Stress-test the claim that [named entity] was responsible for [incident]. Produce the hypothesis matrix and identify the alternative that best survives the evidence."

Argumentative

"Pressure-test the analytic judgment that [trajectory] is most likely. Show which pieces of evidence are load-bearing and which alternatives remain viable."

Argumentative

"Given the evidence at hand, produce an ACH on the cause of [observed pattern]. Identify hypotheses, weight the evidence, name the weakest."

Argumentative

"Adjudicate between two competing explanations of [event]. Rank by consistency with available evidence."

// ANATOMY

A standalone Argumentative product contains:

An Argumentative product looks like a worksheet, not a memo. The visual centerpiece is a matrix: hypotheses on the top row, evidence down the left column, consistency ratings in every cell. The method, developed by Richards Heuer at CIA in the 1970s and refined since, is designed specifically to counteract confirmation bias. It works by focusing on disproving alternatives rather than proving the preferred hypothesis — the hypothesis with the fewest pieces of inconsistent evidence is the one that survives, not the one with the most supporting evidence.

§ 01

Claim Under Test

The specific claim being adjudicated

§ 02

Hypotheses

The set of competing explanations (≥3, preferably 5+)

§ 03

Evidence Inventory

Every relevant piece of evidence, classified for credibility

§ 04

Diagnostic Matrix

The hypothesis-by-evidence grid, with consistency markers

§ 05

Inconsistency Analysis

Per-hypothesis count of inconsistent evidence

§ 06

Surviving Hypothesis

The one with the least inconsistent evidence

§ 07

Confidence Assessment

How much of a margin the surviving hypothesis has

§ 08

Sensitivity Check

What single piece of evidence, if wrong, would flip the result

// HYPOTHESES, TESTED

The matrix is the work.

ACH MATRIX

// VISUAL · PHASE 2B

// WORKED EXAMPLE

From question to brief.

// THE KIQ

"Pressure-test the claim that [event] was produced by [hypothesized cause]. Develop the full set of alternatives and identify which best survives the evidence."

// PIPELINE TRACE

// INTAKE
PIOT complete. Claim: [event] ← [hypothesized cause]
Alternatives required: 3+ competing explanations

// DECOMPOSITION (unique to Argumentative)
Hypothesis development:
  H1 (claim under test)
  H2 (alternative cause A)
  H3 (alternative cause B)
  H4 (combined/compound cause)
  H5 (null hypothesis / coincidence)

Evidence inventory: 31 items
  · Primary source documents: 14
  · Secondary reporting: 11
  · Structured data observations: 6

// MATRIX POPULATION
For each (hypothesis, evidence) pair:
  consistent / inconsistent / ambiguous / not-applicable

Matrix: 5 × 31 = 155 cells
Populated with citations

// ANALYSIS
Inconsistency counts:
  H1: 9 · H2: 4 · H3: 11 · H4: 6 · H5: 14

Surviving hypothesis: H2 (alternative cause A)
  Margin over H1: 5 inconsistencies
Sensitivity: flip on Evidence-17; second-most sensitive Evidence-23

// OUTPUT
Short adjudication report: 1,240 words, 155-cell matrix.

// SAMPLE OUTPUT EXCERPT

The surviving hypothesis (H2) has an inconsistency count of 4, a five-point margin over the hypothesis under test (H1, inconsistency count 9). This margin is sensitive to two pieces of evidence. Evidence-17 (a public statement by [named source]) is the single most load-bearing piece: if its interpretation is revised from "inconsistent with H1" to "consistent with H1," the inconsistency counts compress to H1:8, H2:5, and the surviving hypothesis switches back to the original claim.¹ Evidence-23 is the second-most sensitive;² the remaining 29 items move the inconsistency counts by less than two points in any reasonable re-interpretation. We therefore assess the adjudication outcome as robust to normal analytic disagreement but fragile to a specific re-interpretation of a single source. This is flagged as a known weakness of the analysis.

// TRADECRAFT

ACH is designed to produce the answer you didn't want.

The method is Heuer's.

Analysis of Competing Hypotheses was developed by Richards J. Heuer, Jr., a CIA veteran, in the 1970s, and formalized in his book Psychology of Intelligence Analysis. It is the IC's canonical response to confirmation bias. The matrix structure — hypotheses across, evidence down, consistency markers at each intersection — is his specification, not our invention. We automate the evidence inventory and the cell population; the reasoning is his.

Heuer · Psychology of Intelligence Analysis (CIA, 1999)

The winning hypothesis is the least-disproven, not the most-supported.

ACH's defining move is to focus on evidence that refutes each hypothesis, not evidence that supports it. The hypothesis with the fewest inconsistent pieces of evidence is the one that survives. This is counterintuitive and it is the whole point. "Most supporting evidence" is a confirmation-bias trap; ACH closes that trap by design.

Structured Analytic Techniques (Heuer & Pherson, 2014)

Every cell cites its source.

No "holistically consistent"; no "generally supports." The consistency rating in each cell of the matrix is a specific analytic judgment about a specific piece of evidence, and it carries a source citation. A reader can disagree with a cell; they cannot disagree with the matrix as a whole without naming the cell that is wrong.

ICD 206 · Cell-level sourcing

Runs inside every other engine's pipeline. Also available as a standalone workflow.

// AUTHORED BY