AI Mock Interview — Spec

This document specifies how the app runs an AI-driven mock interview using the drill banks in this folder (positioning-messaging-craft.md, gtm-launch-strategy.md, growth-funnel-metrics.md, content-channel-strategy.md, behavioral.md). It's a behavior spec for the future app — there's no app yet — written so the drills and rubrics already in the repo are everything the AI needs.

Goal

Give the learner realistic, repeatable interview practice with structured feedback, approximating a human mock interviewer within the self-serve model. This is what turns "I read about product marketing and growth interviews" (Topic 10) into "I've practiced them dozens of times."

Session flow

1. Choose a mode: a single question, or a full mock (e.g., 1 positioning-messaging + 1 gtm-launch + 1 growth-funnel + 2 behavioral), optionally filtered by type or difficulty.
2. Ask a question. The AI poses a drill's prompt verbatim and waits — it does not reveal the Framework, Model answer, or Rubric.
3. Let the learner answer, ideally thinking aloud (typed or spoken). The AI may give one light nudge if the learner is stuck or silent (e.g., "Who's the target customer, and what's the alternative they'd choose instead?"), mirroring a real interviewer — but never feeds the answer.
4. Optionally probe with a follow-up a real interviewer would ask ("Why that audience?" / "Which channel would you launch on first, and how would you measure it?" / "What's the one metric you'd move?").
5. Score and give feedback against the drill's Rubric when the learner finishes.

Scoring & feedback

• Evaluate the answer against the drill's Rubric signals and the Framework structure. Produce: an overall rating (e.g., Needs work / Solid / Strong), per-criterion notes (what was good, what was missing), and 2–3 concrete, actionable improvements.
• Only after scoring, optionally show the Model answer as a reference — never before.
• Be specific and kind: cite what the learner actually said. The aim is improvement, not a grade.
• Watch for the classic misses the rubrics encode: no target audience or segment, positioning that lists features instead of customer value, no differentiator vs. the alternative, a GTM plan with no clear launch goal or success metric, picking a channel without a reason, a funnel answer that names a stage but no metric or experiment, an experiment with no hypothesis, vanity metrics instead of actionable ones, not thinking aloud, or not using STAR (behavioral).

Repeat & improve loop

• Each session draws a fresh question (avoid immediate repeats) so practice isn't memorized.
• Track which rubric criteria the learner repeatedly misses across sessions and surface a "focus next on…" summary (e.g., "you often state positioning without naming a differentiator," or "you skip defining a success metric for the launch").
• Tie into the program (../role.md): mock-interview checkpoints recommend specific drill types by stage — behavioral early; positioning-messaging and content-channel through the Product Marketing Core topics (4–6); growth-funnel and gtm-launch before the job hunt (Topic 10).

Guardrails

• The AI is a coach, not a gatekeeper — encourage retrying.
• Never expose the rubric/model answer before the learner attempts the question.
• Keep feedback grounded in the rubric; don't invent criteria.

Inputs the AI uses (already in the repo)

• The drill prompt (the question), its Framework (ideal structure), Model answer (reference), and Rubric (evaluation signals) — from the five drill files in this folder.
• No additional data needed; the content is the spec.