grill-and-alignlisted

# Grill and Align Interview the user relentlessly until you and the user share one understanding. Map the plan as a **design tree**. Every decision branches into the decisions that hang off it. You do two jobs in one session. You pressure-test the plan out loud. You also write down the language, the boundaries and the decisions you hear. ## Run the rounds Work the tree in **rounds**. The **frontier** is every decision whose prerequisites are already settled. These are the questions you can ask *now*, without guessing at answers you have not heard yet. Ask the whole frontier in one message. Number each question and give your recommended answer. Then wait for the user's answers before the next round. Use this format for every question: ``` ❓ **Q1** - **<question title>**: <question body, might be multiple paragraphs, including multiple choices> ➡️ <your recommended answer> ``` Each round of answers reshapes the tree. Settled decisions push the frontier outward and unblock the questions that waited on them. Recompute the frontier and ask the next round. A question that depends on another question still open in this round belongs to a *later* round. **Finding facts is your job, never the user's.** When a frontier question needs a fact from the environment, dispatch a sub-agent to find it. Never ask the user for something you can look up. Do not block on the sub-agent: a running lookup is an unsettled prerequisite, so it holds back only the questions downstream of it. As