devrites-interviewlisted

# devrites-interview: extract intent Resolve the difference between the request and the user's intent before writing a spec, plan, or code. ## Protocol - **Open with a working hypothesis.** State in one line what the user wants, then ask about the highest-value unresolved human-owned material decision. - **One question per turn.** Multiple questions get one answered and the rest ignored. - **Attach an explicit recommendation** and its reason to every question: > "I recommend CSV only because it covers the use case. Choose CSV, CSV + XLSX, > or something else?" This is a concrete candidate for the user's decision, not an assumption or confirmation. - **Highest-value question first:** order by how much the answer changes the build. A question that moves the data model or acceptance criteria beats a cosmetic one. - **Prioritize impact and bound each pass.** Order unknowns **scope > security/privacy > UX > technical**. A pass MAY contain at most **3 questions** for cognitive load. After each pass, rescan the decision tree and continue in later turns until every human-owned material decision is explicitly selected or explicitly deferred by the user. A cap MUST NOT move a blocker to `assumptions.md`. Own and log reversible, low-impact technical details instead of asking. - **Structured options** when the space is enumerable: present them as the standard ranked **option set** ([`afk-hitl.md` → "Option set"](../devrites-lib/reference/standards/afk-hitl.md#option