ns-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.

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, hardware docs, etc.), hand the lookup to a fresh-context agent, or look it up inline if none is available. Ask the user only for what you can't look up yourself. Keep the round moving: a running exploration is an unsettled prerequisite, so only the questions downstream of it wait for its 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. Act on it only after the user confirms you have reached a shared understanding.