Model Combination
Core rule: Combine only when each model answers a different named question. Cap at three, name the conflict rule before applying, then synthesize once.
When to Use
- One model already applied (or clearly primary) still leaves a material blind spot that another mechanism covers.
- Problem spans domains (e.g. risk + choice + system structure) and stakes justify multi-lens work.
- You need independent checks, not confirmation of the same conclusion.
- You can name a distinct role per model before running them.
When NOT to Use
- A single catalog skill fully answers the unknown — apply that skill alone.
- Routine, local, or fully reversible work where multi-lens cost exceeds upside.
- You cannot state what unique question each extra model answers (checkbox / model soup).
- Near-duplicate mechanisms (two diagnosis skills that ask the same causal question).
- Time budget cannot support genuine synthesis — prefer one honest model over contradictory partials.
Procedure
- State the unknown and the gap. Write the decision question. If one model already covers it, stop and use that model alone. Otherwise name the specific blind spot (e.g. "failure modes unexamined", "displaced alternative unknown").
- Pick 2–3 models with distinct roles. For each, record: model id, role (narrow / decide / stress / cost / …), and the unique question it answers. Drop any model that only rephrases another. Prefer sequential pipeline (narrow → stress → decide) over parallel unless independent concurrent checks are required.
- Lock the relation and conflict rule before applying. Choose pattern: sequential, parallel, nested (macro→meso→micro), or adversarial (for/against). Predeclare the tiebreaker (e.g. reversibility class, evidence strength, ruin constraint, primary decision owner). Incompatible worldviews run sequential or adversarial — never blended.
- Apply each model fully for its role only. Capture one key insight per model plus what only that model revealed. Do not re-run a model that adds no new insight.
- Synthesize once. Record convergence, divergence, how the conflict rule resolves divergence, and a single combined recommendation with residual uncertainty. Stop when the recommendation is decision-ready or when further models would only reconfirm.
Output
problem: <decision question>
gap: <named blind spot justifying combination>
pattern: sequential | parallel | nested | adversarial
models:
- id: <skill>
role: <named job>
unique_question: <what only this answers>
insight: <key finding>
conflict_rule: <predeclared tiebreaker>
convergence: <where models agree>
divergence: <where they conflict + resolution>
recommendation: <single decision-ready answer>
stop_reason: gap_closed | single_model_suffices | budget
Verification
- Falsify / stop: Remove a model only when it changes none of the recommendation, supporting evidence, confidence, residual risks, or mitigations; then re-synthesize with fewer. If no predeclared conflict rule exists and models disagree, do not average — pick one primary model or stop and re-route.
- Over-application guard: Never exceed three models. Never add a model for thoroughness theater. If the first adequate single model already closes the gap, combination is wrong for this task.
1---2name: thinking-model-combination3description: When one mental model leaves a material blind spot on a multi-domain or high-stakes problem, sequence complementary models with named roles and a conflict rule.4---5
6# Model Combination
7
8**Core rule:** Combine only when each model answers a different named question. Cap at three, name the conflict rule before applying, then synthesize once.
9
10## When to Use
11
12- One model already applied (or clearly primary) still leaves a material blind spot that another mechanism covers.
13- Problem spans domains (e.g. risk + choice + system structure) and stakes justify multi-lens work.
14- You need independent checks, not confirmation of the same conclusion.
15- You can name a distinct role per model before running them.
16
17## When NOT to Use
18
19- A single catalog skill fully answers the unknown — apply that skill alone.
20- Routine, local, or fully reversible work where multi-lens cost exceeds upside.
21- You cannot state what unique question each extra model answers (checkbox / model soup).
22- Near-duplicate mechanisms (two diagnosis skills that ask the same causal question).
23- Time budget cannot support genuine synthesis — prefer one honest model over contradictory partials.
24
25## Procedure
26
271. **State the unknown and the gap.** Write the decision question. If one model already covers it, stop and use that model alone. Otherwise name the specific blind spot (e.g. "failure modes unexamined", "displaced alternative unknown").
282. **Pick 2–3 models with distinct roles.** For each, record: model id, role (narrow / decide / stress / cost / …), and the unique question it answers. Drop any model that only rephrases another. Prefer sequential pipeline (narrow → stress → decide) over parallel unless independent concurrent checks are required.
293. **Lock the relation and conflict rule before applying.** Choose pattern: sequential, parallel, nested (macro→meso→micro), or adversarial (for/against). Predeclare the tiebreaker (e.g. reversibility class, evidence strength, ruin constraint, primary decision owner). Incompatible worldviews run sequential or adversarial — never blended.
304. **Apply each model fully for its role only.** Capture one key insight per model plus what only that model revealed. Do not re-run a model that adds no new insight.
315. **Synthesize once.** Record convergence, divergence, how the conflict rule resolves divergence, and a single combined recommendation with residual uncertainty. Stop when the recommendation is decision-ready or when further models would only reconfirm.
32
33## Output
34
35```text
36problem: <decision question>
37gap: <named blind spot justifying combination>
38pattern: sequential | parallel | nested | adversarial
39models:
40 - id: <skill>
41 role: <named job>
42 unique_question: <what only this answers>
43 insight: <key finding>
44conflict_rule: <predeclared tiebreaker>
45convergence: <where models agree>
46divergence: <where they conflict + resolution>
47recommendation: <single decision-ready answer>
48stop_reason: gap_closed | single_model_suffices | budget
49```
50
51## Verification
52
53- **Falsify / stop:** Remove a model only when it changes none of the recommendation, supporting evidence, confidence, residual risks, or mitigations; then re-synthesize with fewer. If no predeclared conflict rule exists and models disagree, do not average — pick one primary model or stop and re-route.
54- **Over-application guard:** Never exceed three models. Never add a model for thoroughness theater. If the first adequate single model already closes the gap, combination is wrong for this task.
gabrielmoreira