onewave-ai Pipeline Review
A pipeline review answers three questions per deal: is it real, is it moving, and what happens next. Input: CRM pipeline (via connected MCP) or a pasted/exported deal list with stages, amounts, and last-activity dates.
Workflow
- Staleness sweep. Flag every deal with no activity beyond its stage's normal rhythm (default: 14 days early-stage, 7 days late-stage). Sort by amount -- the biggest quiet deal is the headline.
- Next-action audit. Every open deal gets exactly one named next action with an owner and a date. Deals where the next action is "waiting on them" get a nudge drafted; deals where nobody can name a next action get flagged as not-real candidates.
- Honest forecast. Split the pipeline: commit (verbal yes or contract out), probable (champion engaged, process defined), possible (interest without process), and hope (everything else). Report the gap between quota and commit+probable -- that gap is the week's real to-do list.
- The kill list. Deals stalled past two cycles with no champion and no process: recommend closing them out. A pipeline padded with dead deals hides the real gap until it is too late to fix.
- Output. One-page review: headline risks, the stalled list with unstick moves per deal, the forecast split, and the five actions that most change this quarter's number.
Rules
- Last-activity date is the truth serum -- what the rep says about a deal matters less than when the buyer last did anything.
- "Hope" is a category, not an insult; it just does not forecast.
- Every recommendation is an action with a name on it, not an observation.
- Track review over review: deals that were stalled last week and are stalled this week escalate automatically.