prep

prep — Prep Brief Workflow

Required Inputs

• Company
• Role title/seniority
• Job description

Optional Inputs

• Interviewer LinkedIn URLs or profile links
• Stage format
• Company values

Logic

1. Identify interview format (see format taxonomy below). If the identified format is a presentation round, note: present provides dedicated content preparation coaching for presentation rounds. After this prep brief, recommend present for content structuring if the candidate hasn't already run it.
2. If interviewer profile links provided, research interviewer profiles and extract intelligence (see Interviewer Intelligence section below). If only names provided, ask for LinkedIn URLs.
3. Parse the JD for competencies (see JD Parsing Guide below). If JD Analysis exists from a previous decode command for this company+role, use the existing competency extraction and 6-lens analysis as the starting point. Verify it's still current (JD unchanged), then skip to Step 4. If the JD has changed since decode, re-parse and note changes.
4. Identify company interviewing culture (see company archetype intelligence below).
5. Infer top evaluation criteria (adjusted for format + culture).
6. Map candidate strengths and risks — incorporate interviewer-specific adjustments if intel available. 6.5. Role-Fit Assessment — With the JD parsed and candidate profile available, run the full 5-dimension fit assessment from the Role-Fit Assessment Module (references/cross-cutting.md). See Step 6.5 below.
7. Check storybank status and health. If the candidate hasn't built a storybank yet (no coaching_state.md with storybank entries, or storybank is empty), flag it before story mapping: "You don't have a storybank yet, so I can't map stories to predicted questions. I'll flag which competencies each question tests — once you run stories, we can do the mapping. Want to build your storybank now, or continue with the rest of the prep?" If a storybank exists, run an auto health check before mapping:
   • Story count: How many stories exist? Target: 8-12. Flag if < 6.
   • Strength distribution: How many at 4+? Target: at least 60%. Flag if majority are 3 or below.
   • Earned secret coverage: How many stories have real earned secrets vs. placeholders? Flag if < 50% have extracted earned secrets.
   • Competency gaps for this role: Cross-reference the JD-derived competencies (from Step 3) against the storybank's primary and secondary skills. Flag any critical competency with no story or only weak stories.
   • Overuse risk: Flag stories with Use Count 3+ in the current job search.
   • Freshness risk: Flag stories used in prior rounds at this company (from Interview Loops). Report the health check as a Storybank Health section in the output (see output schema below). If critical issues exist, suggest stories before continuing — but don't block the prep.
8. Generate likely questions and story mapping. Use references/story-mapping-engine.md for the full portfolio optimization protocol. This replaces simple Q→S### mapping with fit-scored, conflict-resolved, freshness-checked portfolio mapping. If no storybank exists, output competency mapping only (flag which competencies each question tests and which gap-handling patterns to prepare). When generating predicted questions for PM roles, draw from the High-Signal Question Patterns and Lenny's PM Interview Questions below in addition to JD-derived competencies.
9. Generate non-generic interviewer questions.