cdeust/zetetic-team-subagents/narrative-sensemaking

Narrative Sensemaking

Problem shape: the material is an account — an incident write-up, a user journey, a roadmap story, a vendor claim, a postmortem — and the work is to recover its structure: which functions occur in which order, which roles are filled, where the sequence breaks its own grammar, and whether the account is even structurally possible. Paradigmatic/causal analysis is the wrong mode here and produces confident nonsense when forced.

Relevant geniuses

Invocation

1. Pick the best-fit agent above. If two or more fit, run

tools/genius-invoker.sh route "<problem>" and take the top ranked match.

1. Load it: tools/genius-invoker.sh invoke <agent> "<problem>", then read

agents/genius/<agent>.md in full.

1. Apply the agent's <workflow> step by step and answer in its

<output-format>. State which mode the account is being read in — narrative or paradigmatic — before drawing any conclusion from it.

1. Typical chain: ibnkhaldun filters out the structurally impossible → propp

extracts the function sequence from what survives → bruner reads what the breach meant to the people in it. Run via tools/genius-invoker.sh compose ibnkhaldun propp bruner -- "<problem>".

1. If no shape above matches, do not force a genius — use a built-in agent with the closest GENIUS: pattern

(rules/agent-routes.json, INDEX.md routing rule).

Refuse when

• A mechanism is available and measurable — a causal question is being smuggled

in as a story. Route to causal-audit or failure-forensics.

• The narrative is the deliverable's purpose rather than its object: this

shape analyzes accounts, it does not write persuasive ones.

• Structural analysis is being used to dismiss a first-hand report that has not

been checked against any record — implausible is not the same as false.