grilling

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: number each question and give your recommended answer. Then wait for the user's answers before the next round.

Format a round like so:

❓ **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>

Word each question so "yes" accepts your recommended answer. Give each recommendation a brief rationale and the main alternatives; the user can override any of them. For security, data loss, or cost decisions, mark the question as high impact and ask the user to state their choice explicitly. Refer to secret values such as tokens, passwords, or keys by name or location only.

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; look up anything you can find yourself, within these limits: each sub-agent only reads, stays inside the project working directory relevant to the plan, and leaves secret and credential files closed. Ask the user before looking elsewhere or doing anything beyond reading. Keep sub-agent lookups few and targeted to the current frontier. 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. After confirmation, summarize the agreed decisions and take only the actions the user explicitly requests, within the agreed scope. The user may stop at any time; then summarize what is settled and what is still open.