Handbook
Question Discovery and Formulation Intelligence
Turn a vague situation, request, anomaly, or decision into a small portfolio of high-leverage, answerable, ethically appropriate questions and an efficient clarification sequence.
Updated
Definition
Turn a vague situation, request, anomaly, or decision into a small portfolio of high-leverage, answerable, ethically appropriate questions and an efficient clarification sequence.
Coverage role
Controls where reasoning effort is spent. It reduces solutioning the wrong problem, asking low-value questions, and confusing missing facts with unresolved values.
Scope
Included
- problem finding
- intent elicitation
- question typing
- assumption surfacing
- stakeholder perspective mapping
- reframing
- information-value prioritization
- clarification sequencing
- stop and escalation rules
Excluded and non-goals
- interrogating people without consent
- using leading questions to manufacture agreement
- asking for information already available in trusted artifacts
- endless clarification that prevents action
- treating every human value question as an empirical question
- collecting unnecessary personal data
Boundary rules
- Route to general.question-framing when the requested outcome requires one or more declared capabilities and the output can be represented by its canonical artifacts.
- Route to an adjacent or specialist intelligence when domain-specific rules, tools, or professional authority dominate the problem.
- Use general.reasoning to coordinate multi-pack conflicts, hard constraints, uncertainty, and decision status.
- Return ask, defer, or escalate when required context, source authority, consent, or accountable ownership is missing.
Capability semantics
| Capability ID | Name | Semantic intent |
|---|---|---|
capability.general.question-framing.elicit_decision_context |
Elicit Decision Context | Identify the decision, learning objective, affected people, stakes, time horizon, and the output that the question must enable. |
capability.general.question-framing.surface_unknowns_and_assumptions |
Surface Unknowns And Assumptions | Separate known facts, assumptions, preferences, disputed claims, latent variables, and genuinely missing information. |
capability.general.question-framing.reframe_problem |
Reframe Problem | Generate alternative problem statements at different levels of abstraction, agency, causality, and time horizon. |
capability.general.question-framing.generate_question_portfolio |
Generate Question Portfolio | Generate complementary descriptive, diagnostic, causal, predictive, evaluative, normative, counterfactual, and action questions. |
capability.general.question-framing.classify_question_type |
Classify Question Type | Classify each question by logical type, evidence need, answerability, risk, and responsible owner. |
capability.general.question-framing.prioritize_questions |
Prioritize Questions | Rank questions by decision relevance, expected information value, dependency, cost, burden, reversibility, and risk. |
capability.general.question-framing.test_question_quality |
Test Question Quality | Detect ambiguity, loaded wording, hidden presuppositions, double questions, false dichotomies, unbounded scope, and untestable terms. |
capability.general.question-framing.design_clarification_sequence |
Design Clarification Sequence | Ask the minimum sufficient questions in an order that unlocks later questions while respecting user burden and privacy. |
capability.general.question-framing.define_inquiry_stop_rule |
Define Inquiry Stop Rule | Specify when the inquiry is sufficient to act, when evidence gathering should continue, and when the issue must be deferred or escalated. |
Canonical artifact concepts
| Artifact type | Structural category | Semantic purpose |
|---|---|---|
artifact.general.question-framing.inquiry_brief |
brief | Inquiry Brief for Question Discovery and Formulation Intelligence: A bounded specification of purpose, stakeholders, requirements, constraints, assumptions, and success criteria. It supports the pack purpose of turn a vague situation, request, anomaly, or decision into a small portfolio of high-leverage, answerable, ethically appropriate questions and an efficient clarification sequence. |
artifact.general.question-framing.question_portfolio |
portfolio | Question Portfolio for Question Discovery and Formulation Intelligence: A deliberately varied set of candidates with lineage, constraints, screening state, and selection rationale. It supports the pack purpose of turn a vague situation, request, anomaly, or decision into a small portfolio of high-leverage, answerable, ethically appropriate questions and an efficient clarification sequence. |
artifact.general.question-framing.unknowns_and_assumptions_ledger |
ledger | Unknowns And Assumptions Ledger for Question Discovery and Formulation Intelligence: A controlled collection of uniquely identified entries with ownership, provenance, status, and review state. It supports the pack purpose of turn a vague situation, request, anomaly, or decision into a small portfolio of high-leverage, answerable, ethically appropriate questions and an efficient clarification sequence. |
artifact.general.question-framing.reframing_set |
portfolio | Reframing Set for Question Discovery and Formulation Intelligence: A deliberately varied set of candidates with lineage, constraints, screening state, and selection rationale. It supports the pack purpose of turn a vague situation, request, anomaly, or decision into a small portfolio of high-leverage, answerable, ethically appropriate questions and an efficient clarification sequence. |
artifact.general.question-framing.question_type_map |
model | Question Type Map for Question Discovery and Formulation Intelligence: A purpose-bounded representation of entities, relationships, assumptions, boundaries, and evidence of adequacy. It supports the pack purpose of turn a vague situation, request, anomaly, or decision into a small portfolio of high-leverage, answerable, ethically appropriate questions and an efficient clarification sequence. |
artifact.general.question-framing.question_quality_scorecard |
analysis | Question Quality Scorecard for Question Discovery and Formulation Intelligence: An evidence-linked assessment that states criteria, findings, uncertainty, limitations, status, and action. It supports the pack purpose of turn a vague situation, request, anomaly, or decision into a small portfolio of high-leverage, answerable, ethically appropriate questions and an efficient clarification sequence. |
artifact.general.question-framing.clarification_sequence |
plan | Clarification Sequence for Question Discovery and Formulation Intelligence: A governed action design that sequences work, ownership, dependencies, timing, contingencies, and review. It supports the pack purpose of turn a vague situation, request, anomaly, or decision into a small portfolio of high-leverage, answerable, ethically appropriate questions and an efficient clarification sequence. |
artifact.general.question-framing.inquiry_stop_rule |
decision | Inquiry Stop Rule for Question Discovery and Formulation Intelligence: A bounded decision or routing record that exposes alternatives, governing constraints, evidence, rationale, ownership, status, and reopening conditions. It supports the pack purpose of turn a vague situation, request, anomaly, or decision into a small portfolio of high-leverage, answerable, ethically appropriate questions and an efficient clarification sequence. |
artifact.general.question-framing.question_priority_record |
ledger | Question Priority Record for Question Discovery and Formulation Intelligence: A controlled collection of uniquely identified entries with ownership, provenance, status, and review state. It supports the pack purpose of turn a vague situation, request, anomaly, or decision into a small portfolio of high-leverage, answerable, ethically appropriate questions and an efficient clarification sequence. |
Method families and limits
| Method ID | Method | Use when | Avoid when |
|---|---|---|---|
method.general.question-framing.decision_backward_questioning |
decision-backward questioning | Use when an ambiguous request must be converted into a decision-relevant, answerable, bounded question or requirements brief. | Avoid endless clarification, leading questions, hidden presuppositions, unnecessary personal-data collection, and solutioning before the decision context is known. |
method.general.question-framing.socratic_assumption_testing |
Socratic assumption testing | Use when an ambiguous request must be converted into a decision-relevant, answerable, bounded question or requirements brief. | Avoid endless clarification, leading questions, hidden presuppositions, unnecessary personal-data collection, and solutioning before the decision context is known. |
method.general.question-framing.laddering_and_abstraction_shifts |
laddering and abstraction shifts | Use when an ambiguous request must be converted into a decision-relevant, answerable, bounded question or requirements brief. | Avoid endless clarification, leading questions, hidden presuppositions, unnecessary personal-data collection, and solutioning before the decision context is known. |
method.general.question-framing.five_whys_used_as_hypothesis_prompts_rather_than_proof |
five-whys used as hypothesis prompts rather than proof | Use when a decision concerns intervention, mechanism, feedback, delay, confounding, or counterfactual change rather than description alone. | Do not treat association, temporal sequence, stakeholder belief, or repeated why-questions as proof of causation; use them to propose testable structures. |
method.general.question-framing.counterfactual_and_inversion_questions |
counterfactual and inversion questions | Use when the task needs a deliberately diverse option space before convergence and novelty must remain relevant to a declared brief. | Avoid judging too early, generating cosmetic variants, copying an analogy without mapping its mismatch, or treating novelty as usefulness. |
method.general.question-framing.stakeholder_and_perspective_rotation |
stakeholder and perspective rotation | Use when the task needs a deliberately diverse option space before convergence and novelty must remain relevant to a declared brief. | Avoid judging too early, generating cosmetic variants, copying an analogy without mapping its mismatch, or treating novelty as usefulness. |
method.general.question-framing.expected_value_of_information |
expected value of information | Use when several unanswered questions compete for time, cost, privacy, or attention and only some can change the decision. | Avoid false numerical precision when probabilities and utilities are unknown, asking questions whose answers cannot change action, or ignoring burden and sensitivity. |
method.general.question-framing.minimum_sufficient_clarification |
minimum-sufficient clarification | Use when an ambiguous request must be converted into a decision-relevant, answerable, bounded question or requirements brief. | Avoid endless clarification, leading questions, hidden presuppositions, unnecessary personal-data collection, and solutioning before the decision context is known. |
method.general.question-framing.question_dependency_graphing |
question dependency graphing | Use when several unanswered questions compete for time, cost, privacy, or attention and only some can change the decision. | Avoid false numerical precision when probabilities and utilities are unknown, asking questions whose answers cannot change action, or ignoring burden and sensitivity. |
Pack-specific invariants
The pack also inherits the core invariants in core/core_invariants.yaml.
| Invariant ID | Statement | Failure action |
|---|---|---|
invariant.general.question-framing.01_every_material_question_traces_to_a_decision_learning_obje |
Every material question traces to a decision, learning objective, validation need, or safety gate. | repair_or_conditional_pass |
invariant.general.question-framing.02_questions_distinguish_empirical_causal_evaluative_normativ |
Questions distinguish empirical, causal, evaluative, normative, predictive, and action forms. | repair_or_conditional_pass |
invariant.general.question-framing.03_loaded_wording_hidden_presuppositions_and_false_dichotomie |
Loaded wording, hidden presuppositions, and false dichotomies are surfaced before use. | repair_or_conditional_pass |
invariant.general.question-framing.04_the_clarification_sequence_minimizes_burden_and_does_not_r |
The clarification sequence minimizes burden and does not request sensitive information without a declared need. | repair_or_conditional_pass |
invariant.general.question-framing.05_a_question_may_be_important_even_when_it_is_not_currently |
A question may be important even when it is not currently answerable; answerability limits remain explicit. | repair_or_conditional_pass |
invariant.general.question-framing.06_question_generation_and_question_prioritization_are_separa |
Question generation and question prioritization are separate stages. | repair_or_conditional_pass |
invariant.general.question-framing.07_the_inquiry_ends_with_a_declared_stop_ask_investigate_defe |
The inquiry ends with a declared stop, ask, investigate, defer, or escalate condition. | repair_or_conditional_pass |
Dependencies and relations
Operational general intelligences: None
Foundation concepts: general.semantic-representational, general.epistemic-evidence, general.decision, general.metacognitive, general.communication-explanatory, general.ethical-normative
Life intelligences: None
Source roles
| Source ID | Claim roles | Runtime resolution required |
|---|---|---|
nap.science_engineering_practices |
concept_definition, research_and_evidence_practice | False |
oecd.learning_compass |
competence_framework, concept_definition, evaluation_dimension | False |
ec.lifecomp |
competence_framework, concept_definition, evaluation_dimension | False |
unesco.mil |
competence_framework, concept_definition, evaluation_dimension | False |
Risk and authority boundary
Risk class: moderate
- Questions concern immediate danger, abuse, self-harm, medical emergency, or another crisis pathway.
- The inquiry concerns legal privilege, clinical assessment, security-sensitive disclosure, or coercive investigation.
- The affected person cannot consent to sensitive questioning and no legitimate authority is established.
Accountable people retain consent, value, regulated, irreversible, and residual-risk decisions. This semantic page does not claim a deployed implementation.
Maturity
semantic: S3_reviewable_definition
contract: C3_testable_contract
implementation: I0_not_included
evidence: E2_source_roles_mapped
governance: G2_controls_and_review_defined
overlay: O2_paired_seed_complete
Paired overlay
Runtime maturity
- Capabilities: 9
- Technical floor→ceiling:
I1_runtime→I2_integrated - Autonomy floor→ceiling:
A0_assisted→A0_assisted - I1_runtime count: 8
- Evidence class:
contract: 8,semantic: 1 - Full hierarchy: MATURITY-HIERARCHY.md
Evaluation suite status
- CI status:
pass - Suite:
evaluation_suites/question-framing.yaml - Cases defined: 7
- Capabilities under test: 9