domain-sensemaking

To turn vague questions into structured workflows, this skill frames the problem with a problem card, generates ranked exploration frontiers, and runs auditable rounds to collect evidence. It validates convergence before synthesizing a reader-calibrated conclusion into a final memo.

Domain sensemaking is a structured research process that uses abduction, triangulation, and Bayesian updating to convert ambiguous questions into auditable workflows. You need it to systematically collect evidence, track claims, and validate convergence before synthesizing conclusions.

Yes, this platform-neutral workflow operates with local files, user notes, papers, and datasets to build a knowledge graph. It captures source notes and tracks claims to produce structured relations and a visual map of your collected evidence.

The best way to track contradictions during synthesis is to maintain a reproducible local workspace using structured files like contradictions.csv and claims.csv. This enables falsification checks and validates evidence convergence before producing a final synthesis.

Yes, the workflow supports Consulting, Decision-making, Learning, and Research/Engineering modes. It coordinates hypothetico-deductive loops and Bayesian updating to produce reader-calibrated conclusions tailored to your specific analytical context.

To operationalize research questions for falsification checks, frame the problem with a problem card and define a clear target outcome. The workflow coordinates abduction and hypothetico-deductive loops to run reproducible, auditable exploration rounds.