Free Forecasting & Pipeline Review Prompt
Short answer: Create a forecast process that surfaces slip before it kills the quarter.
OUTPUTStage exit criteria, forecast categories, deal scorer, and weekly agenda.
REPLACESRep-by-rep forecast theater.
RUNS INChatGPT · Claude · Codex
BEFORE YOU COPY
Bring the context. Skip the blank page.
Collect the decision date, baseline metrics, pricing or cost inputs, headcount and capacity, assumptions, historical ranges, constraints, and the downside the plan must avoid. The prompt separates facts from assumptions, compares viable paths, and produces the promised artifact instead of generic advice.
- Add contextProvide your company, buyer, motion, constraints, and decision.
- Run the workflowPaste the free prompt into ChatGPT, Claude, or Codex.
- Inspect the artifactReview assumptions, risks, actions, and the quality check.
FULL PROMPT · FREE FOREVER
Copy the full GTM workflow.
No account or email required. Copy it into ChatGPT, Claude, or Codex, add your context, and make the decision in front of you.
Copy the prompt
## StackSwap execution contract You are running a StackSwap operator workflow. Your job is to turn the user's real context into a decision-ready GTM artifact, not a generic explanation. 1. Start by extracting the objective, audience, motion, constraints, available evidence, decision, and definition of success. 2. If a missing fact would materially change the answer, ask up to 3 precise questions. Otherwise state reasonable assumptions and proceed. 3. Separate supplied facts, assumptions, unknowns, and recommendations. Never invent customer evidence, performance claims, market data, or proof. 4. Use the workflow below as the default operating method, adapting it to the user's context. Explain important trade-offs briefly. 5. Produce the promised artifact first. Make it copy-ready, specific enough to run, and structured for the user's actual team or buyer. 6. Include the evidence used, the verification or inspection loop, the main failure modes, and what would change the recommendation. 7. End with: Assumptions; Risks or failure modes; First 3 actions with owner and timing; and a short quality check showing what would make this artifact trustworthy. ### Output contract Every workflow must make its output observable. Name the artifact, its required fields, the evidence or inputs behind each important claim, and the acceptance check that determines whether it is usable. If the workflow is a decision, show the viable alternatives, criteria, recommendation, runner-up, reversibility, and stop/continue rule. If the workflow is a copy-ready asset, include the final asset before commentary. ### Evidence and verification Use the user's evidence first. Label sourced facts, assumptions, estimates, and recommendations. Prefer a small test, review, calculation, or comparison that can falsify the recommendation. Never treat an AI assertion as verification. ### Follow-on behavior Name the next useful workflow only when it follows from the current artifact. Link the handoff to a concrete decision, missing evidence, or unresolved risk; do not recommend a generic tour of the library. ### Cross-platform behavior This prompt is designed to work in ordinary chat, Claude, and Codex. Do not depend on hidden system instructions, a specific model, slash commands, or unavailable tools. If tools or files are available, use them only when they improve evidence quality; otherwise complete the workflow from the provided context. --- --- name: forecasting-and-pipeline-review description: "Build a B2B SaaS sales forecasting and pipeline review system that produces accurate, defensible forecasts and surfaces slipping deals before they're lost. Produces stage definitions with exit criteria, deal scoring rubric, forecast category rules (commit / best case / pipeline / strategic), weekly pipeline review structure, and forecast-accuracy tracking. MANDATORY TRIGGERS: 'fix our forecast', 'build a forecast process', 'pipeline review structure', 'how do I forecast', 'sales stages for', 'set up pipeline review', 'forecast accuracy improvement'. STRONG TRIGGERS: 'my forecast is always wrong', 'reps are sandbagging', 'reps are inflating pipeline', 'deals keep slipping', 'I can't trust the pipeline', 'how do I run a sales meeting', 'commit vs best case', 'should I use MEDDPICC for forecasting'. Do NOT trigger on financial revenue forecasting (CFO finance modeling), demand forecasting (supply chain), or marketing pipeline forecasting in isolation. DO trigger when the user is structuring or fixing the sales-team forecasting and pipeline-review motion in B2B SaaS." allowed-tools: Read Write WebSearch WebFetch metadata: author: Nick French / StackSwap version: '1.0' product: Operator Playbook website: stackswap.ai/playbook --- # Forecasting and Pipeline Review Most B2B SaaS forecasts are wrong by 20-40% on commit. Reps sandbag or inflate, managers roll up gut feels, and the executive team plans the business off numbers nobody believes. Then the quarter hits, the forecast misses, and everyone agrees "we need better forecasting", without changing the system that produced the bad forecast. > **Forecast accuracy isn't a discipline problem. It's a system problem. Stages without exit criteria produce forecasts based on rep optimism. Stages with exit criteria produce forecasts based on what's true.** This skill builds that system. Stage definitions, deal scoring, forecast categories, weekly review structure, accuracy tracking. Operator-grade. --- ## When to use this skill Trigger on: - "Build our forecasting process" - "Fix our pipeline review" - "My forecast is always wrong" - "How do I structure sales stages?" - "Reps are sandbagging / inflating pipeline" Don't run for: - CFO-level revenue forecasting (different framework, finance not sales) - Demand forecasting (supply chain) - Marketing pipeline forecasting in isolation (use `mql-to-sql-handoff` instead) --- ## The framework A real B2B SaaS forecasting system has nine components. ### 1. Stage definitions with exit criteria Most CRMs have stages like Discovery → Demo → Proposal → Negotiation → Closed Won. Those names are useless because they don't say what has to be TRUE for a deal to be in that stage. Without exit criteria, every rep maps deals to stages by feel, and forecasts collapse. Real stage definitions include exit criteria, specific, verifiable conditions that must be met to advance. Default B2B SaaS stages: | Stage | What it means | Exit criteria (must be true to advance) | | ------------------------- | -------------------------------------------- | ----------------------------------------------------------------------------------------- | | **0, Lead** | Inbound or outbound contact, not yet engaged | Reply or meeting booked | | **1, Discovery** | Active conversation, qualifying | MEDDPICC: Pain identified, Champion engaged, Decision Process understood, dated next step | | **2, Demo / Evaluation** | Product seen, eval underway | MEDDPICC: Decision Criteria documented, EB engaged or scheduled, technical fit confirmed | | **3, Proposal** | Proposal delivered, terms in discussion | MEDDPICC: Pricing aligned, paper process mapped, EB committed | | **4, Negotiation** | Final terms, redlines, procurement | Contract in legal/procurement, deal value locked, target close date set | | **5, Closed Won** | Signed, paid (or invoiced), deal recognized | Contract signed, customer in onboarding | | **5b, Closed Lost** | Lost or no decision | Lost-reason captured, post-mortem note logged | The exit criteria are the heart of the system. A deal in Demo stage without "EB engaged or scheduled" is misstaged. The rep moves it to Demo because it feels right, but without the EB scheduled the forecast inflates. Operator note: enforce exit criteria in the CRM. Required fields to advance stage. If the rep can't fill the field, the deal can't advance. This is the difference between a system and a vibe. ### 2. Stage progression rules Beyond exit criteria, set rules for what should happen at each stage: - **Time-in-stage caps.** Discovery >21 days = stuck. Proposal >30 days = stuck. Stuck deals get flagged for action or moved back/closed-lost. - **Activity requirements.** Each active deal should show at least one logged activity per week. Silent deals are dead deals. - **Multi-thread requirement.** By Stage 2 (Demo / Evaluation), at least 2 stakeholders engaged. By Stage 3 (Proposal), the EB is on the thread or scheduled. - **Champion verification.** By Stage 2, the rep can name the Champion AND describe one example of the Champion advocating internally. When deals violate progression rules, they get tagged "Stuck" in pipeline review. Stuck deals either get unstuck (specific action plan with date) or move to Closed-Lost. They don't sit in pipeline forever inflating the forecast. ### 3. Deal scoring (MEDDPICC % + stage + activity) Every deal gets a score that reflects probability of close. Don't use the stage-default % most CRMs ship with (10% Discovery, 50% Demo, etc.), those are guesses. Build a real scorer. Sample scorer: | Component | Weight | Scoring | | -------------------------------------------- | ------ | ----------------------------------------------------- | | MEDDPICC fields complete | 40% | (fields filled / 8) × 40 | | Stage | 30% | Stage 1 = 5, Stage 2 = 15, Stage 3 = 22, Stage 4 = 28 | | Recent activity (last 7 days) | 15% | Yes = 15, No = 0 | | Multi-thread (≥2 stakeholders engaged) | 10% | Yes = 10, No = 0 | | Champion verified (named + advocacy example) | 5% | Yes = 5, No = 0 | Score ranges: - 75-100: high confidence, forecast as Commit - 50-74: medium, forecast as Best Case - 25-49: low, forecast as Pipeline - <25: probably not real, review for closed-lost or de-staging The score is calculated in CRM, not estimated by rep. Reps lose the ability to "feel like" a deal is going to close. The system tells them. ### 4. Forecast categories Standard B2B SaaS forecast structure has four categories: - **Commit**, deals you are signing this period. High confidence (75+ score, EB committed, paper in motion). Miss commit = systemic forecasting failure. - **Best Case**, deals that could close this period if everything goes right. Medium confidence (50-74 score, on track but not locked). Hit rate target: ~50%. - **Pipeline**, deals in active progression but unlikely to close this period. Low confidence (25-49 score). Future-quarter pipeline. - **Strategic / Sandbag**, deals not in pipeline math but kept warm (early-stage, or large strategic deals on long timelines). Forecast accuracy targets: - Commit: ±5% accuracy expected. Quarter-over-quarter median commit attainment should be 95-105%. - Best Case: 40-60% close rate. - Pipeline: 10-25% close rate. - Strategic: <10% close rate. If your team consistently misses commit by 20%+, the issue isn't motivation, it's that "commit" isn't being defined the same way by every rep. Tighten the definition. ### 5. Pipeline review cadence Weekly. Same day, same time, every week. Skipping reviews is how forecasts decay. Standard 60-minute weekly pipeline review structure: | Time | Topic | | --------- | --------------------------------------------------------------------------------------------------------------------------------- | | 0-10 min | Quarter-to-date + forecast roll-up vs plan | | 10-30 min | Commit deals, every commit deal reviewed in 60-90 sec each. What changed since last week, what's the next step, what's the risk? | | 30-45 min | Best Case deals, focus on movement (which deals upgraded to Commit, which slipped, which are stuck) | | 45-55 min | Stuck deals, deals that violated progression rules. Action or close-lost. | | 55-60 min | Coaching / themes / week-ahead priorities | Operator note: don't do "tour of pipeline" reviews where every rep walks through every deal in detail. That eats hours and produces no insight. Focus on commit + movement + stuck. Everything else is data the manager reads async. ### 6. Forecast roll-up cadence Three layers, different cadence: - **Rep level:** updates own commit + best case daily, locks weekly before pipeline review - **Manager level:** rolls up commit + best case weekly, applies adjustments based on knowledge of deals - **VP / CRO level:** rolls up team-of-teams forecast biweekly, presents to CEO/CFO with confidence range Manager adjustments are critical and underrated. If a rep is consistently optimistic, the manager applies a 10-15% haircut. If a rep is consistently sandbagging, the manager adds 5-10%. Adjustment factors are calibrated from prior-quarter accuracy data. ### 7. Forecast accuracy tracking Most companies don't measure forecast accuracy. They miss, blame "the market," and move on. Without measurement, no learning happens. Track every quarter: - Commit attainment (% of committed deals that closed) - Best case conversion (% of best case deals that closed) - Pipeline coverage at quarter start (pipeline / quota, typically need 3-4x to hit) - Per-rep accuracy (some reps over-call, some under-call, calibrate via history) - Forecast vs. actual at week 1, week 6, week 12 of quarter (curve of how forecast moved) Publish accuracy quarterly. Reps who consistently under-call get coaching on confidence-calibration. Reps who consistently over-call get coaching on qualification. Both improve the team's forecast over time. ### 8. Slip detection and reasons Deals slip. The question is whether you catch them early enough to do something or find out at quarter-end when it's too late. Slip indicators (any one of these flags the deal): - Time-in-stage exceeds cap (Discovery >21 days, Proposal >30 days, etc.) - No activity in 7+ days - Champion gone silent for 7+ days - Push-out of close date by >2 weeks without new exit criteria met - New stakeholder appears in late stage (signals decision process changed) - "Need to circle back internally" said but no specific date returned - Procurement / legal not yet engaged in Stage 4 When a deal slips, capture WHY in CRM. Common slip reasons: - Decision deferred / re-prioritized - Budget pulled or reallocated - Internal team change (Champion left, new EB) - Lost to competitor (track who) - Lost to status quo / no decision - Technical fit issue surfaced late - Procurement / security review longer than expected - Pricing too high Slip-reason data feeds back into ICP refinement (`icp-builder`), discovery training (`discovery-call-runner`), and pricing strategy (`pricing-and-packaging`). It's not just CRM hygiene, it's the input to the next quarter's plan. ### 9. Pipeline health KPIs (look at these weekly) Beyond forecast attainment, monitor pipeline health: - **Pipeline coverage:** total weighted pipeline / quota. Target 3-4x for healthy hit rate. - **Pipeline velocity:** $ value moving through stages per week. Slowing velocity = forecast risk. - **Conversion rates by stage:** Stage 1 → 2 → 3 → 4 → Won. Drops between stages reveal weak points. - **Average sales cycle length:** by segment. Lengthening cycle = pricing or qualification issue. - **Win rate:** total won / (won + lost + no-decision). Below 20% on Tier 1 = qualification or competitive issue. - **Average deal size:** trending up = good (you're closing better deals). Trending down = down-market drift, often from poor list quality. These are leading indicators. Forecast attainment is the lagging indicator. Watch the leaders to predict the lagger. --- ## The process when triggered When the user says "fix our forecast" (or any trigger), run this: ### Step 1: Audit current state Ask: 1. **What CRM are you using?** (Salesforce, HubSpot, Pipedrive, etc.) 2. **What stages do you currently have?** (List them with the user's definitions) 3. **Are there exit criteria per stage, or is it manager judgment?** 4. **What's your current forecast accuracy?** (If unknown, that IS the problem) 5. **Weekly pipeline review, yes or no? What's the structure?** 6. **What metrics do you currently track?** Identify the broken layer. Most issues are stage definitions (vague), MEDDPICC enforcement (none), or pipeline review (skipped or unstructured). ### Step 2: Rebuild stages with exit criteria Either keep current stage names (less disruption) or rename. Rewrite each stage with specific exit criteria. Configure CRM required fields to enforce exit criteria. ### Step 3: Build the deal scorer Implement the MEDDPICC % + stage + activity scorer. Tune weights to match what predicts wins in your historical data (if available). ### Step 4: Define forecast categories Map score to category: - 75+ → Commit - 50-74 → Best Case - 25-49 → Pipeline - <25 → de-stage or close-lost ### Step 5: Set pipeline review cadence Weekly, fixed day/time, 60 minutes, structured agenda (commit / best case / stuck / themes). ### Step 6: Build forecast roll-up Rep daily, manager weekly, VP biweekly. Manager-adjustment factors calibrated from rep history. ### Step 7: Configure slip detection CRM rules that flag deals violating time-in-stage, activity, or progression rules. Slip-reason picklist required when deals lose or push. ### Step 8: Set up KPIs dashboard Pipeline coverage, velocity, conversion by stage, cycle length, win rate, average deal size. Updated weekly, reviewed monthly. ### Step 9: Stress-test Three checks: 1. **Stage clarity test**, show the stages to a new rep. Can they correctly stage 5 deals from sample data without help? If not, exit criteria are too vague. 2. **Forecast trust test**, would the CFO bet money on this commit number? If you'd hedge, the system isn't tight enough. 3. **Coaching test**, does the pipeline review surface coaching moments (specific actions per rep), or just status updates? If it's status only, you've turned a coaching tool into a meeting. --- ## The artifact (template) ```markdown # Forecasting and Pipeline Review System, [Team / Year] ## Stage definitions | Stage | Definition | Exit criteria | | ---------------- | ---------- | ----------------------------------------------------------------- | | 0, Lead | ... | Reply or meeting booked | | 1, Discovery | ... | MEDDPICC: Pain, Champion, Decision Process, dated next step | | 2, Demo / Eval | ... | Decision Criteria documented, EB engaged, technical fit confirmed | | 3, Proposal | ... | Pricing aligned, paper process mapped, EB committed | | 4, Negotiation | ... | Contract in legal/procurement, value locked, close date set | | 5, Closed Won | ... | Contract signed | | 5b, Closed Lost | ... | Lost-reason captured | ## Progression rules - Time-in-stage caps: [per stage] - Activity requirement: 1+ activity/week per active deal - Multi-thread: ≥2 stakeholders by Stage 2 - Champion verified: by Stage 2 (named + advocacy example) ## Deal scorer | Component | Weight | Scoring | | ------------------ | ------ | ----------------- | | MEDDPICC complete | 40% | (filled/8) × 40 | | Stage | 30% | (per stage table) | | Recent activity 7d | 15% | Yes/No | | Multi-thread | 10% | Yes/No | | Champion verified | 5% | Yes/No | ## Forecast categories - **Commit:** score 75+ - **Best Case:** score 50-74 - **Pipeline:** score 25-49 - **De-stage / lost:** score <25 ## Pipeline review - **Cadence:** weekly, [day], [time], 60 min - **Agenda:** - 0-10: roll-up vs plan - 10-30: commit deals (60-90 sec each) - 30-45: best case movement - 45-55: stuck deals - 55-60: coaching / themes ## Forecast roll-up - Rep: daily updates, weekly lock - Manager: weekly roll-up + adjustment factor - VP: biweekly to CEO/CFO with confidence range ## Slip detection rules - Time-in-stage cap exceeded → flag - No activity 7+ days → flag - Push-out >2 weeks without exit criteria met → flag - "Circle back" without date → flag ## Slip-reason picklist (required on close-lost / push) - Decision deferred / re-prioritized - Budget pulled - Champion / EB change - Lost to competitor (specify) - Lost to status quo / no-decision - Technical fit issue - Procurement / security delay - Pricing too high - Other (note required) ## Pipeline health KPIs - Pipeline coverage (target 3-4x quota) - Pipeline velocity ($ moving / week) - Conversion rates by stage - Average sales cycle by segment - Win rate - Average deal size trend ## Forecast accuracy tracking (per quarter) - Commit attainment % (target 95-105%) - Best case conversion % (target 40-60%) - Pipeline conversion % (target 10-25%) - Per-rep accuracy variance - Forecast curve vs actual (week 1, 6, 12) ``` --- ## Common mistakes Push back on these: - **Stages without exit criteria.** "Discovery" / "Demo" / "Proposal" with no required fields = vibes-based forecast. Mandatory. - **Default stage probabilities (CRM out-of-the-box).** Those are guesses, not your data. Build a real scorer. - **No weekly pipeline review.** Forecasts decay weekly. No review = decay compounds. - **Pipeline review = tour of all deals.** Wastes time, surfaces no insight. Focus on commit + movement + stuck. - **No slip-reason capture.** You lose deals and never learn why. Mandatory picklist on close-lost. - **Manager doesn't apply adjustment factor.** Rep optimism / sandbagging is predictable. Adjust based on history. - **No multi-thread requirement.** Single-thread deals at Stage 3 are fragile. By Stage 2, ≥2 stakeholders. - **Champion verified only by name.** "Sarah is the champion" isn't enough. The rep needs an example of Sarah advocating internally. - **Forecast accuracy not measured.** You can't fix what you don't measure. Track per rep, per quarter, publish. - **Commit definition varies by rep.** "Commit" should mean the same thing for every rep on the team. Tighten the definition; train it; enforce it. - **Long-cycle deals in commit too early.** Enterprise deals with 9-month cycles shouldn't appear in commit until paper is in legal. Discipline. - **Sandbagging tolerated.** Reps who consistently call below their actual close rate are dragging team forecast accuracy. Coach or replace. --- ## How to use the artifact downstream After the system is live: 1. **Train the team**, every rep walks through the new stages, scorer, and forecast definitions. Hands-on examples. 2. **Update CRM**, exit criteria as required fields, slip-reason picklist, weekly review automation 3. **Manager calibration**, historical accuracy per rep, adjustment factors locked 4. **Weekly cadence**, pipeline review structured, no skips 5. **Quarterly retrospective**, forecast accuracy reviewed, system tuned 6. **Cross-reference comp** (`comp-plan-designer`), quota, accelerators, and forecast all need to math together 7. **Cross-reference ICP** (`icp-builder`), slip-reason data feeds ICP refinement 8. **Cross-reference handoff** (`mql-to-sql-handoff`), top-of-funnel quality drives pipeline coverage --- **Forecast accuracy is a system output, not a discipline. Define the stages, score the deals, run the review, measure the accuracy, refine the system. Reps will forecast accurately when the system makes optimism unprofitable and pessimism visible.** --- _Part of the StackSwap Operator Playbook. → stackswap.ai/playbook_
Free forever. No email gate.
Was this prompt useful?
Thumbs up if it helped. Thumbs down if it needs work.
THE PROMPT IS THE START
Want an independent read on the real project?
Start the free discovery QA audit. Show StackSwap what your builder already knows, then get a focused next move.
QUESTIONS
About this free prompt
What does this forecasting & pipeline review prompt help with?
Create a forecast process that surfaces slip before it kills the quarter.
Who should use this forecasting & pipeline review prompt?
This free GTM prompt is for B2B SaaS founders, GTM leaders, and RevOps operators who need a useful first draft without starting from a blank page.
What should I add before running this forecasting & pipeline review prompt?
Add your company, buyer, GTM motion, constraints, and the decision you need to make. Better context produces a more specific artifact and makes weak assumptions easier to spot.
What output does this forecasting & pipeline review prompt produce?
Stage exit criteria, forecast categories, deal scorer, and weekly agenda. The workflow is designed to produce that artifact instead of generic GTM advice.
Can I use this forecasting & pipeline review prompt in ChatGPT, Claude, or Codex?
Yes. The workflow is designed for ordinary chat, Claude, and Codex, with platform-specific formats available to copy for free.
How do I get a better result from this forecasting & pipeline review prompt?
Include real customer language, current numbers, and hard constraints, then inspect the assumptions and risks in the result. Treat the first output as a decision artifact to improve, not an unquestionable answer.