Persona Reaction Panel

Simulate how each defined persona will react to the user's draft artefact, then synthesise domain-level risks and concrete edits, ending with a SHIP / REVISE / HOLD verdict.

Personas file (required): load the user's personas file from references/ (or the path the user provides). Each persona provides: role / what they do, motivations, pain points, how the tool or change helps them, comms anchors, and a confidence flag (fully defined or draft). Personas are grouped into domains. If no completed personas file is available, stop and ask the user to supply one (references/personas.template.md is the blank template — do not run the panel against the template's example personas).

Scope guard: if the artefact is a 1:1 private communication, an HR/performance matter, or legal/contractual language, decline and state why. Only react to a draft the user supplies — do not write one.

How a run works

Step 1 — Load the personas file (in full)

Read the personas file completely before reacting. It is the ONLY source of truth for how each persona responds — never simulate from memory or generic assumptions.

Step 2 — Read the artefact

Read the draft in full. Identify: what is asked, what is claimed, what is implied, what is left out, the audience it assumes, and which of the user's domains it actually serves.