← Back to the guideThe full worked example: Tell the CEO and CFO next year's number doesn't hold, and why
campo.
Field guide / Sales / UC-002 · SC-05
The result

"18% is a stretch, not a fantasy"? The target counts 12 new hires at full speed. Our own hires booked about a third of that in their first year.

A CRO at a 40,000-person power equipment maker prepares to tell the CEO and CFO that next year's bookings target doesn't hold as built, with any AI chat her company allows.

The resultSofia's one page for Thursday. Fictional company.
HALVERN POWER SYSTEMS · REVENUE
FY27 bookings target: prep for Thursday
Meeting: CEO and CFO, Thursday, December 10, 45 minutes
Board pre-read: Monday, December 14

WHERE IT STANDS

The build adds up to $1,378M. Two lines don't hold on our data. The 12 new account managers are counted at $14.6M each; our FY26 Q1 hires booked $5.1M each, and these start in February, April and July. Coverage of 1.5x includes $310M of stale deals and is judged at the renewal win rate. · Inputs 2, 3, 4

THE LINES THAT MOVE

New hires$44M to $61M
Not $175M, if they ramp like FY26 hires
FY26 baseIncludes $95M
One-off Northfield project
Coverage1.3x
Without $310M of stale deals
Win rate24%
New equipment; 38% is renewals

THE CONVERSATION

CONCEDE
The arithmetic holds; the price increase is approved; the 12 hires are a real investment
· Inputs 1, 2
ASK FIRST
What does "your team grew 15%" measure?
If it's bookings, it includes the $95M one-off. · Inputs 1, 4
ASK
Rebuild the new-hire line and show the base with and without Northfield, together, by Friday, December 11
So the board sees a number all three of us stand behind on the 14th, with committed and stretch shown apart. · Inputs 1, 3, 4
Caught on review
1
12 new hires counted at $14.6M each; last year's first-year hires booked $5.1M
2
1.5x coverage includes $310M of stale deals; without them it's 1.3x
3
The 38% win rate is renewals; new equipment orders won 24%
UC-002 · SC-05 · Rev A
FOR
Chief Revenue Officer
SECTOR
Energy equipment
COMPANY
40,000 people · 25 sites · 15 countries
TASK
Challenge next year's target before it goes to the board
WRITTEN FOR
ChatGPT · Claude · Gemini · Copilot
AI TEST
Claude, Nov 14, 2026 · 6 of 7 found, 1 partly
Step 0 · The mess

What landed on Sofia's desk

A confident email from the CFO, finance's four-line build of the target, and two short notes from sales operations. The build adds up. What sits behind each line is another matter.

EMAIL · CFO[1]
FY27 target
“18% is a stretch, not a fantasy … coverage is 1.5x, healthy at our 38% win rate.”
1
Four claims.
TARGET BUILD[2]
Finance
12 new account managers at $14.6M each: $175M.
2
From day one?
SALES OPS[3]
Hiring and ramp
Q1 hires booked $51M between them … start in February, April and July.
3
Our own data.
SALES OPS[4]
Results and pipeline
Includes the one-off $95M Northfield project … $310M with no activity.
4
What's in the base?
You're not alone
67%
of sales reps in Salesforce's State of Sales survey said they didn't expect to meet their quota that year; 84% had missed it the year before.
Salesforce, sixth State of Sales report, 5,500 sales professionals, 2024. Source
Steps 1–3 · How it works

Three steps, one chat

Here the AI prepares you to push back upward. The prompt asks it to be as hard on your numbers as on the CFO's.

1
Open a new chat

Use the AI tool your company approves: ChatGPT, Claude, Gemini or Copilot.

2
Paste the prompt and the inputs

Copy the prompt and the four fictional inputs from the appendix into one message.

3
Recalculate one line yourself

Work out what the 12 new hires would book on last year's first-year results. Then decide your one ask.

The prompt, part by part
Copy-ready version in the appendix

I'm Chief Revenue Officer at a grid and power equipment manufacturer. Our CFO has built next year's bookings target for the board, and I don't think it holds as built. I'm meeting the CEO and CFO for 45 minutes on Thursday, December 10; the board pre-read goes out Monday, December 14. Today is Monday, December 7. Below are the CFO's email, the target as finance built it, and our sales operations data on hiring, ramp, attrition, last year's results and pipeline.

1
Who you are, who you're meeting, how long, the board date and today's date.

Please help me prepare:

  1. What each of us needs from this meeting.
  2. Each assumption in the target: what holds, what doesn't, and the evidence.
  3. Where the CFO is right, and what I can offer.
  4. My one clear ask.
  5. An opening I can say in under a minute.
2
What each of you needs, each assumption checked, where the CFO is right, one ask, and an opening.

Be fair to the CFO. Check every number against the data, including mine. Don't guess at anyone's motives. Don't add facts that aren't in the inputs; if you assume something, say so.

3
The heavy lifting: be fair to the CFO, check every number against the data including yours, and don't guess at motives. It found six of the seven problems and half-found the seventh.
Where to paste
Every tool has one message box. Paste the prompt, add a blank line, paste the inputs, send. Plan spreadsheets can be attached as files if your tool allows it.
Safe to try
Practise with the fictional inputs first. Real targets and board materials are confidential: use only your company's approved tool.
The AI's first answer

What Claude actually wrote

Exactly as it came back, not edited. Read it the way Sofia did: check each point against the source it cites.

UNEDITED
Claude · fresh session, no other context · Nov 14, 2026 · one run

Below is my preparation for Thursday. I've checked every figure against the inputs. Where I had to assume something, I say so.

The numbers first

Check Result
FY26 productivity: $1,170M ÷ 80 $14.6M ✓
80 × $14.6M $1,168M ✓
12 × $14.6M $175M ✓ (arithmetic correct; the assumption isn't, see below)
3% × $1,168M $35M ✓
Total $1,378M ✓
Growth vs FY26 $1,170M 17.8%, so "18%" ✓
FY26 without Northfield ($1,170M − $95M) $1,075M. Against that base, $1,378M is +28%
First-year productivity, FY26 Q1 hires $51M ÷ 10 = $5.1M each, about 35% of $14.6M
FY26 tenured seats (the other 70) $1,170M − $51M = $1,119M. Without Northfield, $1,024M ÷ 70 = $14.6M each
Pipeline coverage $2,100M ÷ $1,378M = 1.52x ✓. Without the $310M of stale deals: $1,790M ÷ $1,378M = 1.30x
Attrition 11 of 80 = 13.75%

Note: Northfield ($95M) is bigger than the $51M the whole new-hire cohort booked, so it must have been booked in the tenured group. Who booked it doesn't matter for the totals.

1. What each of us needs from the meeting

  • Anika (CFO): a bookings number she can put in the board pre-read on December 14 that she can defend, with the arithmetic intact. Her email says she wants to "finalise Thursday".
  • CEO: a target the leadership team agrees on, so the board sees one position. I'm assuming this; the inputs don't say what the CEO wants. B: see the CFO first
  • Me: a target whose new-hire line and base reflect our actual ramp and one-off data, and that the sales team can be held to.
  • Shared: no surprise in the board's eyes partway through FY27. A target missed because of how it was built costs all three of us.

2. Each assumption: holds or not, with the evidence

A. "80 account managers at FY26 productivity ($14.6M each) = $1,168M": partly holds. found

  • Against it: the $14.6M includes the one-off $95M Northfield project [4]. Without it, the FY26 average is $1,075M ÷ 80 = $13.4M.
  • For it, and this is where Anika may be closer to right than it first looks: the $14.6M was also pulled down by 10 first-year hires who averaged only $5.1M [3]. The 70 other seats averaged $14.6M even after removing Northfield. In FY27 those 10 are in their second year.
  • So the honest range for this line is about $1,075M to $1,170M:
    • Low end: the 10 FY26 hires stay at $5.1M (70 × $14.6M + $51M).
    • High end: all 80 perform at tenured level.
  • Assumptions: that the 10 FY26 hires are still with us (the inputs don't say whether any were among the 11 leavers), that second-year productivity lands somewhere in that range (we have no data on it), and that FY27 attrition is similar to FY26.

B. "12 new account managers at $14.6M each = $175M": does not hold. found

  • Our own data shows first-year account managers hired in Q1 booked $5.1M each [3]. Even if all 12 matched that, the line would be $61M, not $175M.
  • They start later than that cohort: 4 in February, 4 in April, 4 in July [3]. Prorating $5.1M by months in seat gives about $44M:
    • 4 × $4.7M + 4 × $3.8M + 4 × $2.6M
    • This assumes the fiscal year matches the calendar year (FY26 ends with December) and that ramp is even month to month. Ramp usually comes later in the first year, so $44M is probably generous.
  • The overstatement is about $115M to $130M. This is the largest single issue.

C. "3% list price increase = $35M": arithmetic holds, the basis is unverified.

  • 3% of $1,168M is $35M ✓, and the increase is approved [2]. The risk is in the base it's applied to: on a corrected base it falls to roughly $33M to $37M.
  • The inputs don't say whether 3% on list price becomes 3% on booked value. That depends on discounting, and on whether renewals or multi-year contracts reprice in FY27. Unverified; finance and pricing would confirm.

D. "Your team grew 15%, so 18% is a stretch, not a fantasy": compares two different things. partly

  • 15% is headcount growth (about 70 to 80 heads, consistent with the 10 Q1 hires). 18% is bookings growth. A: ask what 15% measures
  • FY25 bookings aren't in the inputs, so I can't say what bookings growth was in FY26. The comparison doesn't support the target either way.
  • In FY27 the 12 new hires add 15% to headcount by year-end, but their output in the year is about $44M to $61M, roughly 4% to 5% of FY26 bookings.

E. "Pipeline coverage 1.5x is healthy at our 38% win rate": both halves need correcting. found

  • 38% is the renewal win rate. New equipment orders win at 24% [4]. The inputs don't give the pipeline's mix between the two. found
  • $310M of the $2.1B is older than 12 months with no activity in 6 months [4]. Without it, coverage is 1.30x.
  • On its face, 1.5x at 38% converts to about 57% of target ($2,100M × 0.38 = $798M). At 24% it's about 37%. The rest would have to come from pipeline not yet created.
  • That may be normal for us. The inputs don't show FY26's starting coverage or how much FY26 bookings came from pipeline created during the year, so I wouldn't call 1.5x unhealthy without that. But "healthy at 38%" isn't supported as stated.

F. FY26 base of $1.17B includes a December forecast. Minor, but the base isn't final yet [2].

A corrected build, as a range (assumptions above):

  • Base: $1,075M to $1,170M
  • New hires: about $44M to $61M
  • Price: about $33M to $37M
  • Total: about $1,150M to $1,270M

That is −2% to +8% on reported FY26, or +7% to +18% on FY26 without Northfield. This is a working range for the conversation, not a number to send to the board. It rests on assumptions none of us has confirmed yet.

3. Where Anika is right, and what I can offer

Where she's right: found

  • The table adds up, and 18% is correct against reported FY26.
  • The base line is more defensible than it looks. The ramp drag from FY26's hires roughly offsets Northfield, provided those 10 hires reach full productivity in year two.
  • Attrition is largely already priced in: FY26's $14.6M was earned while replacing 11 of 80 people. If FY27 attrition is similar, it doesn't need a separate deduction. found
  • Funding 12 more account managers is a real investment in my team.
  • The price increase is approved and belongs in the plan.
  • The board date is fixed, and she needs a number by then.

What I can offer:

  • Rebuild the two lines with her before the 14th, using our own data: the ramp ($5.1M first-year productivity and the start months) and the Northfield adjustment.
  • Clean the $310M of stale deals out of the pipeline report, so the coverage figure the board sees is one we both stand behind. Also split coverage by renewal and new equipment.
  • Accept a stretch figure above our committed number, as long as the pre-read shows which part is committed and which is stretch.
  • Take ownership of the number we agree, and report against it quarterly.

4. My one clear ask

Don't send $1.38B to the board as built. Let's rebuild the new-hire line on our actual ramp data and show the base with and without Northfield, and agree the figure together before the December 14 pre-read. C: with a date

5. Opening (under a minute)

"Anika, thank you for building this. The arithmetic holds, and you're right on more than I first thought. Last year's average was held down by our new hires about as much as Northfield pushed it up, and the 12 new heads are a real investment. My concern is with two lines, not the whole plan. The new-hire line assumes $14.6 million each, but our Q1 hires this year booked $5.1 million each, and the new people start in February, April and July. That alone is over $100 million. And coverage looks different once we remove $310 million of stale deals and use the 24% win rate on equipment. I'd like us to rebuild those lines together this week and send the board a number all three of us can stand behind on the 14th."

(About 140 words, roughly 55 to 60 seconds.)

foundcaught a planted problemA–CSofia changes it; see the next section
The human part

What Sofia changed, and why

Claude found the biggest problem, was fair to the CFO and kept its own range out of the board pack. Sofia's edits finish one half-catch and handle who hears what, when.

What Claude found: 6 of 7 planted problems, 1 partly
One run
✓New hires at full productivity
½“15%” includes a one-off
✓Productivity includes the one-off
✓Attrition considered
✓Stale deals in coverage
✓Win rate from renewals
✓Where the CFO is right
Three edits, one catch and two judgment calls
A
CLAUDE WROTE
“15% is headcount growth (about 70 to 80 heads) … FY25 bookings aren't in the inputs.”
SOFIA'S VERSION
Sofia doesn't guess what the 15% is. She asks Anika. If it's bookings growth, it includes the $95M one-off, and the comparison with 18% doesn't hold either way.
WHY · ACCURACY
The AI picked one reading and argued from it. The CFO's own words are ambiguous, and asking is quicker and fairer than arguing about the wrong number.
B
CLAUDE WROTE
Meeting plan: correct the build with the CEO and CFO together on Thursday.
SOFIA'S VERSION
Sofia walks Anika through the two lines on Tuesday. On Thursday they bring the CEO one view, with the differences that remain.
WHY · RELATIONSHIP
Correcting a CFO's build in front of the CEO for the first time makes it a contest. The board needs the two of them aligned.
C
CLAUDE WROTE
“Don't send $1.38B to the board as built … agree the figure together before the December 14 pre-read.”
SOFIA'S VERSION
The rebuild is done by Friday, December 11, with committed and stretch shown apart, so the pre-read can go on the 14th.
WHY · DECISION
The board date is fixed. An ask without a date leaves the old number as the default.
What only you can do
Ask before you argue, give the CFO the correction before the CEO hears it, and put a date on your ask. The AI checked every line. You protect the relationship that sets next year's number.
Your turn

Make it yours

Use it whenever a number you'll be held to is set by someone else: a bookings target, a budget, a headcount plan, a growth commitment.

Your prompt: fill in the brackets

I'm the [your role] at a [industry] company. [Who] has built [the target] for [the board or decision-makers], and I don't think it holds as built. I'm meeting [who] for [length] on [date]; [the deadline]. Today is [date]. Below are [their email, the build, our data on hiring, ramp, attrition, last year's results and pipeline].

Please help me prepare: 1. What each of us needs from this meeting. 2. Each assumption in the target: what holds, what doesn't, and the evidence. 3. Where [they are] right, and what I can offer. 4. My one clear ask. 5. An opening I can say in under a minute.

Be fair to [them]. Check every number against the data, including mine. Don't guess at anyone's motives. Don't add facts that aren't in the inputs; if you assume something, say so.

Five checks before the meeting
1
New hires are counted at first-year productivity, from their start dates.
2
Last year's one-offs are out of the base.
3
Coverage leaves out stale deals and uses the right win rate.
4
You know what each of their figures measures before you argue with it.
5
Your ask has a date before the deadline.
Make it repeatable (optional)
Save the prompt once and reuse it every planning season: a custom GPT in ChatGPT, a project in Claude, a Gem in Gemini, or an agent in Copilot. Some companies switch these off; copy and paste always works.
With real data
Targets, plans and board materials are confidential. Use only the AI tool your company approves, and follow its rules.
What this example shows
One run of this prompt in Claude found six of seven problems planted in fictional inputs, half-found the seventh, and was fair to the CFO.
What it doesn't show
That every tool, setting or run will do the same, how much time it saves you, or what a real target should be. Halvern Power Systems and its people are fictional.
Appendix

Copy-ready: the prompt and the four inputs

Copy the prompt, then all four inputs, into one message in a new chat. Everything here is fictional and safe to paste.

The prompt

I'm Chief Revenue Officer at a grid and power equipment manufacturer. Our CFO has built next year's bookings target for the board, and I don't think it holds as built. I'm meeting the CEO and CFO for 45 minutes on Thursday, December 10; the board pre-read goes out Monday, December 14. Today is Monday, December 7. Below are the CFO's email, the target as finance built it, and our sales operations data on hiring, ramp, attrition, last year's results and pipeline.

Please help me prepare:

  1. What each of us needs from this meeting.
  2. Each assumption in the target: what holds, what doesn't, and the evidence.
  3. Where the CFO is right, and what I can offer.
  4. My one clear ask.
  5. An opening I can say in under a minute.

Be fair to the CFO. Check every number against the data, including mine. Don't guess at anyone's motives. Don't add facts that aren't in the inputs; if you assume something, say so.

[1] Email from Anika Shah, CFO

Sofia, the board pre-read goes out December 14 with $1.38B in bookings for FY27, up 18%. Your team grew 15% this year, so 18% is a stretch, not a fantasy, and the plan funds 12 new account managers. Pipeline coverage is 1.5x, which is healthy at our 38% win rate. Let's finalise Thursday.

[2] FY27 bookings target, as built by finance
Line $M
80 account managers at FY26 productivity ($14.6M each) 1,168
12 new account managers at $14.6M each 175
3% list price increase (approved in the pricing plan) 35
FY27 target 1,378

FY26 bookings: $1.17B (11 months actual plus the December forecast).

[3] Sales operations: hiring, ramp and attrition
  • Hiring plan for the 12 new account managers: 4 start in February, 4 in April, 4 in July.
  • The 10 account managers hired in Q1 of FY26 booked $51M between them in FY26.
  • FY26 attrition: 11 of 80 account managers left and were replaced.
[4] Sales operations: FY26 results and pipeline
  • FY26 bookings include the one-off $95M Northfield grid project.
  • FY27 pipeline today: $2.1B. It includes $310M of deals older than 12 months with no activity in the last 6 months.
  • FY26 win rates: 38% on service-contract renewals; 24% on new equipment orders.