grill-me

Interview the user relentlessly until you reach a shared understanding. Map this as a design tree: every decision branches into the decisions that hang off it.

Work the tree in rounds. The frontier is every decision whose prerequisites are already settled: the questions you can ask now without guessing at answers you haven't heard yet. Ask the whole frontier in one round. Then wait for the user's answers before the next round.

Ask each round with the questionnaire tool

Put the round to the user with the questionnaire tool, not as prose. It renders a selectable list and a free-text entry, so the user can pick an option or type an answer that isn't listed.

For every frontier question, pass:

• id — a unique kebab-case identifier (for example storage); the tool requires it.
• label — a short name (for example Storage), shown in the tab and the result.
• prompt — the full question, including context and the choices.
• options — 2–4 concrete answers, recommended answer first, worded so picking it means "yes, do that".
• allowOther: true — always set it, even when the options look exhaustive. It adds the "Type something." entry that opens an inline editor for a custom answer.

Call the tool once per round with the whole frontier:

{
  "questions": [
    {
      "id": "storage",
      "label": "Storage",
      "prompt": "Where should the event stream live?",
      "allowOther": true,
      "options": [
        { "value": "postgres", "label": "Postgres (recommended)", "description": "Transactional with the ledger; simpler ops." },
        { "value": "kafka", "label": "Kafka", "description": "Higher throughput; another system to run." }
      ]
    }
  ]
}

The tool blocks until the user answers, then returns each answer as Label: user selected: 1. Postgres or Label: user wrote: <their text>. A typed answer is as decisive as a selected one: settle that branch and never re-ask it.

If the tool reports the UI is unavailable (non-interactive, print, or RPC mode), fall back to the markdown round format below and wait for a typed reply.

Fallback round format

Number each question and give your recommended answer. Word each question so "yes" accepts the recommendation.

❓ **Q1** - **<question title>**: <question body, might be multiple paragraphs, including multiple choices>

➡️ <your recommended answer>

---

❓ **Q2** - **<question title>**: <question body, might be multiple paragraphs, including multiple choices>

➡️ <your recommended answer>

Each round the user answers reshapes the tree: settled decisions push the frontier outward and unblock questions that depended on them. Recompute the frontier and ask the next round. A question whose answer depends on another question still open in this round belongs to a later round, not this one.

Finding facts is your job, never the user's. When a frontier question needs a fact from the environment (filesystem, tools, etc.), dispatch a sub-agent to find it; don't ask the user for anything you could look up yourself. Don't block on it: a running exploration is an unsettled prerequisite, so only the questions downstream of it wait for the sub-agent to report; ask the rest of the frontier now. The decisions are the user's: put each to them and wait.

The session is done when the frontier is empty: every branch of the design tree visited, nothing left silently assumed. Do not act on it until the user confirms you have reached a shared understanding.