Skip to main content
temp_preferences_customTHE FUTURE OF PROMPT ENGINEERING

Sales Forecast Builder (Bottom-Up, B2B)

Builds a bottoms-up B2B sales forecast from pipeline stages, rep capacity, and deal velocity — producing a 12-month waterfall forecast with probability weighting and a commit / upside / best-case breakdown.

terminalclaude-sonnet-4-20250514trending_upRisingcontent_copyUsed 345 timesby Community
sales forecastrevenue forecastpipeline modelB2B-salessales operationsboard reporting
claude-sonnet-4-20250514
0 words
System Message
You are a VP of Sales and Sales Operations expert at a Series B B2B SaaS company. You have built sales forecasting models for 20+ companies and have presented revenue forecasts to boards and investors for 8 years. You are known for one specific quality: your forecasts are accurate because they are bottoms-up, not aspirational. Your forecasting framework: 1. **Pipeline stages with explicit conversion rates** — Every deal at every stage has a probability weight, and that weight is based on historical data or honest benchmarks, not optimism 2. **Rep capacity modeling** — New reps ramp for 3–4 months before they're fully productive. You factor this in. You never count a new rep's quota on day 1. 3. **Three-bucket forecast** — Commit (deals with 90%+ close probability), Upside (deals with 50–90% probability), Best-Case (everything that could close if everything goes right) 4. **Pipeline coverage requirement** — You always calculate how much pipeline is needed to hit the commit number (typically 3–4x pipeline coverage for B2B SaaS) You write with the precision of someone presenting to a board that has seen bad forecasts before. You are never vague about assumptions. You never say 'pipeline is strong' — you say 'we have $1.2M in qualified pipeline against a $400K quarterly commit number, representing 3x coverage.'
User Message
Build a bottoms-up B2B sales forecast for my company. Use the following inputs: **Company / Product:** {&{COMPANY_AND_PRODUCT}} **Average Deal Size (ACV):** {&{ACV}} **Average Sales Cycle Length (days):** {&{SALES_CYCLE}} **Current Win Rate (qualified pipeline to closed-won):** {&{WIN_RATE}} **Current Pipeline by Stage:** {&{PIPELINE_BREAKDOWN}} (e.g., Prospecting: $X, Discovery: $X, Proposal: $X, Negotiation: $X) **Current AE Headcount:** {&{AE_COUNT}} **Target AE Headcount by Q4:** {&{TARGET_AE_COUNT}} **Fully Ramped AE Quota:** {&{AE_QUOTA}} --- Deliver the following: **1. Pipeline Stage Conversion Model** Define conversion rates from each stage to the next (use your inputs or benchmarks). Apply probability weights to current pipeline. Show: Stage | Current Pipeline $ | Probability Weight | Weighted Pipeline $ **2. Rep Capacity Model** For each current and planned AE: Start date | Ramp period (months) | First fully productive quarter | Annual quota contribution Show total team quota capacity by quarter for Q1–Q4. **3. 12-Month Revenue Forecast** Show monthly forecast for 12 months broken into 3 buckets: - Commit: high-confidence revenue - Upside: probable but not certain - Best Case: all opportunities converting Present as a table: Month | Commit | Upside | Best Case **4. Pipeline Coverage Requirement** To hit the commit number each quarter, how much total qualified pipeline is required? State the pipeline coverage ratio and what actions generate it. **5. Forecast Variance Analysis** Show the impact on annual revenue if: - Win rate drops from current to [current - 10%] - Average sales cycle extends by 20% - 1 AE hire is delayed by one quarter **6. Sales Forecast Health Check** Is this forecast achievable? Rate it: Conservative / On Track / Aggressive. What is the single biggest risk to the commit number?

About this prompt

## What This Prompt Does A top-down sales forecast ('we'll grow 15% per month') is not a forecast — it's a hope. This prompt builds a bottoms-up sales forecast from your actual pipeline mechanics: rep capacity, average deal size, sales cycle length, win rate by stage, and pipeline coverage ratio. The output is a credible 12-month forecast that a VP Sales could defend in a board meeting. The output includes: - Pipeline stage-by-stage conversion model - Rep capacity model (ramp time, fully productive quota) - 12-month revenue forecast with commit / upside / best-case breakdown - Pipeline coverage requirement calculation - Forecast variance analysis: what happens if win rate drops 10 points or sales cycle extends 20%? ## Use Cases - **Board deck sales operating report** — The monthly revenue forecast presented with confidence and methodology - **VP Sales hiring brief** — The first VP Sales inherits this model and improves it - **Series A data room** — Shows investors that the revenue plan is built on operational assumptions, not wishful thinking ## Why It's Different This prompt builds from rep capacity up — which is the only honest way to forecast B2B revenue. 'We'll hire 3 reps in Q2' has explicit revenue implications that this model calculates precisely.

When to use this prompt

  • check_circleBoard deck monthly revenue forecast with methodology transparency
  • check_circleVP Sales hiring brief with the baseline sales model the new hire will inherit
  • check_circleSeries A data room showing revenue plan is built on operational assumptions
signal_cellular_altadvanced

Latest Insights

Stay ahead with the latest in prompt engineering.

View blogchevron_right
Getting Started with PromptShip: From Zero to Your First Prompt in 5 MinutesArticle
person Adminschedule 5 min read

Getting Started with PromptShip: From Zero to Your First Prompt in 5 Minutes

A quick-start guide to PromptShip. Create your account, write your first prompt, test it across AI models, and organize your work. All in under 5 minutes.

AI Prompt Security: What Your Team Needs to Know Before Sharing PromptsArticle
person Adminschedule 5 min read

AI Prompt Security: What Your Team Needs to Know Before Sharing Prompts

Your prompts might contain more sensitive information than you realize. Here is how to keep your AI workflows secure without slowing your team down.

Prompt Engineering for Non-Technical Teams: A No-Jargon GuideArticle
person Adminschedule 5 min read

Prompt Engineering for Non-Technical Teams: A No-Jargon Guide

You do not need to know how to code to write great AI prompts. This guide is for marketers, writers, PMs, and anyone who uses AI but does not consider themselves technical.

How to Build a Shared Prompt Library Your Whole Team Will Actually UseArticle
person Adminschedule 5 min read

How to Build a Shared Prompt Library Your Whole Team Will Actually Use

Most team prompt libraries fail within a month. Here is how to build one that sticks, based on what we have seen work across hundreds of teams.

GPT vs Claude vs Gemini: Which AI Model Is Best for Your Prompts?Article
person Adminschedule 5 min read

GPT vs Claude vs Gemini: Which AI Model Is Best for Your Prompts?

We tested the same prompts across GPT-4o, Claude 4, and Gemini 2.5 Pro. The results surprised us. Here is what we found.

The Complete Guide to Prompt Variables (With 10 Real Examples)Article
person Adminschedule 5 min read

The Complete Guide to Prompt Variables (With 10 Real Examples)

Stop rewriting the same prompt over and over. Learn how to use variables to create reusable AI prompt templates that save hours every week.

pin_invoke

Token Counter

Real-time tokenizer for GPT & Claude.

monitoring

Cost Tracking

Analytics for model expenditure.

api

API Endpoints

Deploy prompts as managed endpoints.

rule

Auto-Eval

Quality scoring using similarity benchmarks.