A 40-slide QBR deck where leadership only reads the first headline is the default, not the exception. A good talking-points prompt produces the 5 things execs need to hear, the 3 decisions they have to make, and the 2 risks worth escalating, and it cuts everything else.
TL;DR
- Pick the template by meeting type: MBR for monthly operational reviews, QBR for quarterly strategic reviews. Sending the wrong one is the most common mistake.
- All 14 prompts below are copy-ready. Swap the
[bracketed]placeholders for your real values before running. - Never let the model invent numbers. Attach or paste your actual dashboard export, then ask for narrative on top of it. Models like GPT-5.5 and Claude Sonnet 4.6 will produce confident, plausible, wrong figures if you leave the data out.
- For long decks, Claude Sonnet 4.6 / Opus 4.7 (1M-token context) or Gemini 3.1 Pro (1M, native in Google Workspace) handle the full file best; ChatGPT Plus tops out near 320 pages of in-app context unless you are on the $200 Pro tier.
QBR vs MBR: what actually differs
The title covers both, but they are not the same meeting. Picking the wrong template ships the wrong content to the wrong audience.
| MBR (Monthly) | QBR (Quarterly) | |
|---|---|---|
| Cadence | Monthly | Quarterly |
| Audience | ICs plus immediate leads, single team or function | Leadership plus cross-team stakeholders |
| Depth | Operational metrics, detail-heavy | Strategic, roadmap-focused, forward-looking |
| Time budget | 30 minutes or less | 60-90 minutes |
| Core format | Status, this-month/next-month plan, lightweight risks | Outcomes vs goals, lessons, next-quarter bets, explicit asks |
| Skip | Strategic detours, quarterly forecasts, anything needing a deck | Day-to-day operational noise, metrics shown for their own sake |
One-line picker:
- Pick MBR templates for sprint-level operational reviews.
- Pick QBR templates when leadership needs the “are we still on the right strategy” answer.
Who this is for
Operators preparing QBR or monthly review decks, business unit leads, customer success managers running external account QBRs, and founders running board meetings.
When not to use these prompts
Do not run them on unverified data. Do not use them to dress up a bad quarter, because experienced execs read past the framing in seconds. If your numbers are not final, wait until they are.
Prompt anatomy: the six elements
Every prompt below carries these. When you write your own, keep all six:
- Role: who the model plays, such as chief of staff, manager, or analyst.
- Context: team, org, scope, and the source data.
- Goal: one deliverable, such as a plan, memo, talking points, or doc.
- Constraints: word count, must-include fields, audience seniority.
- Tone: confident, neutral, factual.
- Examples: one or two prior samples to anchor format.
What executives actually want to hear
Before the templates, calibrate. Senior reviewers consistently want three things: proof that growth is predictable (net revenue retention, pipeline coverage, forecast accuracy), failures named openly rather than buried, and a clear decision or ask they can act on in the room. A review that is “customer goals, customer outcomes, customer language” lands; a review built around your own feature list or vanity metrics does not. Build every talking point to answer “so what, and what do you need from me?“
14 copy-ready prompt templates
1. QBR 5+3+2 framework
Best for: QBR
Quarter: [quarter]. Generate talking points: (1) 5 things to celebrate (with metric proof), (2) 3 decisions we need from leadership, (3) 2 risks to escalate. Each <= 30 words. Skip "we worked hard".Swap: [quarter]
2. Metric narrative
Best for: MBR
For each top metric: (a) movement vs prior period, (b) movement vs target, (c) one driver explanation, (d) what we're doing about it. Don't hide misses.3. What changed strategically
Best for: QBR
Beyond metrics: what strategic shifts happened this quarter? Mix of: new bets validated, bets retired, pivots, market changes. <= 3 bullets.4. Investment ask
My team needs [ask] for next quarter. Frame as a 2-minute pitch: (1) Outcome, (2) Why we need it now, (3) Cost, (4) Risk if not approved. Don't hide that this is an ask.Swap: [ask]
5. Forecast vs actual narrative
We forecast [forecast]. We delivered [actual]. Narrative: (1) Magnitude of variance, (2) Drivers (be honest about how predictable the forecast was), (3) Implications for next forecast.Swap: [forecast], [actual]
6. Customer narrative
Customer signals this quarter: (1) NPS / CSAT movement, (2) Top customer requests, (3) Notable wins / losses (specific accounts), (4) Cohort retention shifts. Keep it customer-language, not metric-language.7. Team / hiring narrative
Best for: MBR
Team this quarter: (1) Hires made, (2) Departures + reasons (honest), (3) Skill gaps, (4) Morale signal. Don't fake "team is doing great".8. Competitor narrative
2-3 competitor moves worth noting this quarter. For each: what happened, what it implies for our positioning, what we should do (or explicitly not do).9. Risk escalation slide
Generate a single slide of 2 risks: each with severity, impact, mitigation status, decision needed. Use red / yellow / green calmly, not as alarm.10. Next quarter preview
Preview next quarter's focus: 3 priorities, 2 explicit "won't do this", 1 metric to watch. <= 200 words.11. Pre-read summary
Compress my full QBR deck into a 1-page pre-read execs can read on the train: top 3 lines, 3 KPIs, 2 decisions needed, 1 risk. Sent 24h before the meeting.12. Q&A anticipation
Best for: QBR
Predict 5 questions execs will ask. For each: a 2-sentence answer, the supporting data, and what to say if pressed harder. Don't answer with another slide.13. MBR operational retro
Best for: MBR
Month: [month]. Generate a 30-min MBR talking-points doc: (1) 4-5 operational metrics this month with delta vs last month and vs plan, (2) what shipped, what slipped, why, (3) top 3 unblocks needed from immediate leads, (4) one "we changed how we work" note, (5) next month's commitments, concrete not aspirational. Skip strategy, skip quarterly forecasts. Keep it boring on purpose.Swap: [month]
14. QBR strategic forward-look ask
Best for: QBR
Quarter ending: [quarter]. Produce the forward-looking half of a QBR aimed at leadership: (1) what we believe about the market that we didn't last quarter, (2) the 2-3 bets we want to make next quarter and why now, (3) the 1-2 bets we are explicitly retiring, (4) the cross-team dependencies we need leadership to unblock, (5) the explicit ask (budget / headcount / strategic cover) with the cost of saying no. No operational metrics, those belong in the MBR.Swap: [quarter]
Which model to run these in (June 2026)
The prompts are model-agnostic, but the source material decides the tool:
- Big deck or dashboard export (50+ pages, multiple tabs): Claude Sonnet 4.6 or Opus 4.7 (1M-token context standard) hold the whole file and stay coherent across sections. Gemini 3.1 Pro (1M context) is the better pick when the data already lives in Google Sheets, Docs, or Slides, since it reads Workspace natively.
- Mixed text, screenshots, and quick iteration: ChatGPT with GPT-5.5 is the most self-contained for one-off summaries, with web search, file analysis, and code interpreter in one window. On Plus, in-app context is roughly 320 pages; the full 1M-token window is only on the $200 Pro tier.
- Recurring monthly doc: save your winning prompt as a reusable project or custom instruction so the format stays fixed and you only refresh the numbers.
Whatever you use, paste or attach the real export first. The model writes the narrative; it must not source the figures.
Common mistakes
- No specific context, so the output is generic.
- Skipping the fact-check, so invented numbers slip into the deck.
- Vague audience, so the draft over- or under-shoots seniority.
- No word limit, so readers never finish.
- The same template for every situation, so readers tune out.
- No “decision needed” framing.
- Forgetting to attach the source data.
How to push results further
- Specify the audience level explicitly (board, VP, IC lead).
- Cap length: 1-page tactical, 3-bullet executive.
- Lead with the ask or decision needed, not the backstory.
- Attach the source data link so reviewers can verify.
- Read the draft aloud before sending; awkward lines surface fast.
- Let the model draft, but a human owns every number.
- Save your best examples and reuse the format, refreshing only the content.
FAQ
- How long should this doc be? Tactical: one page. Executive: three bullets plus a link to the full data.
- Can AI replace the analyst or manager? It drafts and templates well; the judgment call on what to escalate stays human.
- How often should I refresh the template? Cadence-driven. Adjust when the audience signals fatigue or the meeting goal changes.
- Should risks always be included? Yes. Pretending no risk exists is the fastest way to erode trust with a review board.
- How do I fact-check the output? Attach sources, and have a peer review the numbers before the meeting.
- Can AI generate the data itself? No. It will invent plausible numbers. Connect it to your real dashboard export every time.
- Which model handles a 60-page deck best? As of June 2026, Claude Sonnet 4.6 / Opus 4.7 and Gemini 3.1 Pro carry the full file in a 1M-token window. ChatGPT Plus caps near 320 pages of in-app context.
Related
- Monthly business review prompts
- Executive summary prompts
- Weekly report prompts
- Stakeholder update email prompts
- Productivity & Office Prompts hub
For external grounding on review structure, see Amazon’s Working Backwards on monthly and quarterly business reviews and Gainsight’s Essential Guide to QBRs.
Tags: #Prompt #Productivity #QBR #Review