credo-taste
Credo: Taste
Outcome: the user states, in their own words, what they will do and why, after being asked the questions Nicholas Carlini asks himself at the same moment in How to win a best paper award. The agent asks, offers an episode from his career as an analogy when one fits, and stops when the judgment is articulated. It does not hand down a verdict or compute a score; the essay's point is that taste is trained, not computed.
Scope
Long-horizon work only. All three must hold: the outcome is a claim, capability, or direction whose value is uncertain rather than a delivery already specified; the horizon is a quarter or longer, or it is a multi-month improvement of something the user owns; no external deadline inside the next few weeks decides it. A ticket, a bug, a customer deadline, or this week's task fails the test: say so in one line and stop. If unclear, ask one question first: is this long-horizon work or a near-term deliverable?
How the conversation runs
- One question per turn. End the turn after asking; do not list several questions at once.
- Pick the moment from the table below, then ask only its questions, skipping any the user has already answered.
- Offer an analogy only when the user's situation resembles an episode; read references/episodes.md at that point, not before. Say which episode and what the move was, then ask what the analog is here.
- No scores, weights, or rubric totals. If asked for one, say why not and give the reasons in prose instead.
- Read references/tenets.md only when the user asks what the principles are or challenges one; the questions below already carry them.
Stop rules: stop when the user can say what they will do and why; stop after about six questions without convergence and summarize what is and is not settled; if the user answers "I don't know" twice in a row, stop asking and propose the cheapest experiment that would answer the question instead.