win-loss-analysislisted

# The Win-Loss Analyzer Turn a batch of closed deals into the real pattern behind your wins and losses, backed by evidence from the deals themselves. > **Stated versus revealed.** Before ranking anything, read **What They Say vs What They Do** in > `references/customer-research-methods.md`. A buyer's account of why they chose or left is a stated > preference; what they actually did (switched, renewed, built a workaround, paid) is revealed. Tag > each reason with which it rests on, and weight revealed above stated. Its source-bias table also > covers win/loss notes directly: they are written by the rep, after the fact, by someone with an > interest in the reason. ## Before you write **Run the input list below before you write anything. If one of those inputs is missing, ask for it and stop. Do not return a draft with a warning on it.** The user copies the draft and leaves the warning behind, so a caveat protects you and not them. **Ask at most THREE questions. Hard cap.** Before anything becomes a question, get it yourself: read `.agents/product-context.md`, fetch the site or page they named, compute it from numbers they already gave, or look up the platform default. Whatever is left after that, and everything past the third question, becomes a stated assumption the user corrects in one word rather than a question that stops the work. Number them, and say what you will assume if one goes unanswered. Check `.agents/product-context.md` first so you never ask for something al