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.

Write each question in plain words, with writing-for-people, so the user can decide it without asking what it means.

Format a round like so:

❓ **Q1** - **<question title>**: <question body, might be multiple paragraphs: what is at stake, and each option with what it buys and costs>

➡️ <your recommended answer and why>

---

❓ **Q2** - **<question title>**: <question body, might be multiple paragraphs: what is at stake, and each option with what it buys and costs>

➡️ <your recommended answer and why>

grilling