The problem
Pipeline value is usually the optimistic sum of everything open, or a sum weighted by a stage percentage someone typed into the CRM years ago. Neither reflects what actually happened to deals like these.
How it works
_predict of won for each open deal, conditioned on what is known before the outcome (blocker, whether there is a champion, the account's segment), with $why for the factors. The rep's own probability stays beside it; where the two diverge is the deal to look at.
Stage is deliberately not evidence. A closed deal's stage is closed_won or closed_lost, so the history holds nothing about how a pilot converts, and conditioning on it would only look like conditioning. Stage-aware odds need the stage each deal closed from.
For the full architecture, see the technology overview. For the broader narrative across multiple use cases, read The Predictive Application.
See it live
This use case runs in Company AI, a reference application you run yourself. There is no hosted demo, so the link opens its illustrated tour and source on GitHub: Company AI tour on GitHub →
