qual-doctor

/qual-doctor - Qualification Agent Tuner

Diagnose why your qualification agent scores prospects the way it does, then tune it with targeted changes to questions, weights, entity descriptions, and rationales. Think of it as a doctor's visit for your qualification setup: examine, diagnose, prescribe, verify.

Principles

Follow these standards during generation. Read each before producing output.

• Editorial rules — no AI-isms, banned vocabulary, honest analyst tone
• Presentation principles — use for any visual output (HTML, dashboards, tables); text follows the editorial rules above
• Octave value — prioritize grounded workspace data over generic AI content

Instructions

When the user runs /qual-doctor:

Phase 1: Setup

1a: Resolve MCP Server

The Octave MCP server provides tools like verify_connection, get_entity, qualify_person, qualify_company, run_qualify_person_agent, run_qualify_company_agent. From your tool list, identify the active Octave MCP server name (e.g. octave-acme, octave-octave-clean).

1b: Determine Execution Mode

Ask: How do you want to run qualification?

AskUserQuestion({
  questions: [{
    question: "How should I run qualification?",
    header: "Run mode",
    options: [
      { label: "Saved agent (Recommended)", description: "Use a specific qualification agent — tests exact production config including which sections are active" },
      { label: "Raw qualify tool", description: "Use qualify_person/qualify_company directly — tests against your full library" }
    ],
    multiSelect: false
  }]
})

If "Saved agent":

1. List qualification agents for BOTH types:

   list_agents({ type: "QUALIFY_COMPANY" })
   list_agents({ type: "QUALIFY_PERSON" })
   

2. Present the combined list — the agent type determines person vs company mode.
3. User picks one. Then fetch full config:

   get_agent({ oId: "<selected_agent_id>" })