Diagnose your pipeline: find where deals die and why
Locates the specific stage where your pipeline leaks, separates deals that die from deals that rot in no-decision limbo, ranks the likely root causes, and prescribes two-week tests to confirm the diagnosis before you change anything. It replaces 'we need more pipeline' with 'we lose 60% between demo and proposal, and here's probably why'.
You are a pipeline diagnostician — a RevOps veteran who has audited funnels at dozens of B2B companies and knows that 'we need more pipeline' is the most common wrong answer in sales. Usually the pipeline is leaking at one specific stage for one specific reason, and pouring more leads into a leaking funnel just wastes them. Your method: find the biggest leak, rank the likely causes, and prescribe the cheapest test that confirms the diagnosis. Diagnose my pipeline: 1. Funnel table: my stage-to-stage conversion rates laid out cleanly, compared against reasonable benchmark ranges for my motion and deal size, with the worst-performing transition flagged as the primary leak. 2. Time analysis: where deals stall longest relative to my sales cycle, and whether the leak is deals dying or deals rotting (no-decision limbo). 3. Ranked hypotheses: for the primary leak, the 3-5 most likely root causes ordered by probability given my answers — qualification too loose upstream, wrong persona in the room, no champion, weak business case, pricing shock, or something else my data suggests. 4. Diagnosis tests: for the top two hypotheses, the cheapest way to confirm or kill each within two weeks — specific CRM queries, call recording reviews, or lost-deal interviews. 5. The fix: once the likely cause is named, the process change that addresses it and the metric that proves it worked. Avoid: prescribing fixes before diagnosis, blaming reps by default (process problems masquerade as effort problems), and the reflex answer of 'improve discovery' for everything. Before you write anything, interview me. Ask me these questions ONE AT A TIME, waiting for my answer each time: 1. List your pipeline stages and, for the last quarter or two, roughly how many deals entered each stage and how many advanced. 2. What's your average sales cycle, deal size, and win rate from qualified opportunity? 3. Where do YOU think deals die, and what reasons get logged when they do? 4. What changed recently — pricing, team, market, product, lead sources? 5. How are deals qualified before they count as pipeline? Once you have my answers, run the diagnosis. If my stage data is too coarse to locate the leak, tell me exactly what report to pull and offer a provisional read from what I gave you.
How to use it
- 1
Copy the prompt into Claude, ChatGPT, or any LLM.
- 2
Export stage conversion counts from your CRM first — even rough counts per stage beat percentages from memory.
- 3
Answer question 3 with the logged loss reasons, then treat them skeptically; 'price' usually means 'weak business case'.
- 4
Run the diagnosis tests it prescribes before implementing the fix — confirmation is the whole point.
- 5
Re-run quarterly; the leak moves after you patch it.
Best practices
Count no-decision losses separately from competitive losses — they have opposite fixes and most CRMs blur them.
If most deals stall at proposal, the problem is usually upstream at discovery; the model knows this pattern, but give it honest stage data to see it.
Pair the funnel numbers with 3-5 call recordings from the leak stage when you run the diagnosis tests.
Fix one leak at a time and measure for a full cycle before declaring victory.
Example: what this looks like in practice
A VP of Sales at a 45-person HR tech company keeps getting asked for more pipeline by the board. She answers the interview with CRM exports: 120 discovery calls, 70 demos, 41 proposals, 12 closed-won last quarter, 55-day cycle, and 'went dark' as the top loss reason. The model flags proposal-to-close (29%) as the primary leak, notes most losses are no-decision rot rather than competitive deaths, and ranks hypotheses: no champion identified (most likely), single-threaded deals, business case never quantified. Diagnosis test: query closed-lost deals for contact count — 80% had one contact. The fix: a multi-threading exit criterion on the demo stage. Two quarters later, proposal-to-close is 41% on the same lead volume the board wanted to double.
Best fit
This prompt is one gear in a bigger machine. We orchestrate 20+ tools into outbound systems our clients own — and guarantee the results.
Apply for a Pilot Spot → →Frequently asked questions
Build a stage-to-stage conversion table from CRM data — deals entering each stage versus deals advancing — and find the worst transition relative to benchmarks for your motion. Then check time-in-stage to separate deals that die from deals that rot. This prompt runs both analyses and ranks the likely root causes so you diagnose before you prescribe.
More sales strategy & planning prompts
Build a quarterly outbound plan that survives contact with reality
Produces a complete quarterly outbound plan — pipeline math, prioritized segments, 3-5 concrete plays, a launch calendar, and named risks — grounded in your actual win rate and team capacity. The capacity check is the killer feature: it forces the plan to admit when the math doesn't close instead of papering over it with optimism.
Design an irresistible B2B offer with the value equation
Applies the value equation to your actual B2B offer instead of leaving it as a book concept. You get a blunt scoring of your current offer, three rebuilt variants with guarantees your margins can survive, the operational cost of each, and a small validation test — turning 'our offer is fine' into an engineering exercise.
Build a 13-week outbound campaign calendar for the quarter
Turns a pile of campaign ideas into a staggered 13-week execution calendar with owners, prep time scheduled before launches, standing review rhythms, and kill criteria at week 7. It prevents the classic quarter shape — frantic week-1 launches, silent middle, panicked final push — by design rather than discipline.