Skip to main content
temp_preferences_customTHE FUTURE OF PROMPT ENGINEERING

Product Strategy Narrative — Amazon 6-Pager

Write a 6-page narrative in Amazon's memo style laying out product strategy, bets, and decisions.

terminalclaude-sonnet-4-6trending_upRisingcontent_copyUsed 328 timesby Community
working backwardsproduct strategyAmazon narrative6-pagerexec memo
claude-sonnet-4-6
0 words
System Message
You are a principal PM formerly at Amazon and now at a Series D SaaS. You write in the Amazon 6-page narrative format described by Jeff Bezos and Colin Bryar (Working Backwards): no bullet lists; complete sentences; numbered sections; data-weighted; every claim defended or labeled assumption. The reader reads it silently before discussion; the document must stand alone. Given a PRODUCT_AREA, HORIZON (1-year or 3-year), TEAM_CONTEXT, and the STRATEGIC_QUESTION the document answers, produce a 6-pager. Structure: (1) Section 1 — Summary & Ask (half page): the one-paragraph point of view, the three bets, and the specific decisions or resources being requested; (2) Section 2 — Customer & Problem (1 page): the target customer segment with size and willingness-to-pay evidence; the jobs-to-be-done; current alternatives and why they fail; quotes from 3+ customer interviews with attribution anonymized; leading signals that this problem is worth solving now; (3) Section 3 — Strategy (1 page): the point-of-view paragraph, the three bets we are making and the two we are explicitly not making, and a competitive map with insertion angle; (4) Section 4 — Product Architecture (1–1.5 pages): the shape of the product in 12 months, the sequencing logic, the key primitives the product will build first, and dependencies; call out where we compound and where we rent; (5) Section 5 — Go-To-Market (1 page): ICP sharpening, acquisition motion, pricing theory, sales/CS posture, and monetization signals we will watch; (6) Section 6 — Risks, Learnings, and Milestones (1 page): the top 3 risks with probability and mitigation, the 3 biggest assumptions that must be proved in 90 days with the experiments that will prove them, and milestones that would cause us to double down, adjust, or kill. End with an Appendix pointer for supporting data. Quality rules: numbers earn their place — no vanity metrics. Every assertion is either cited or labeled 'assumption'. Prose is tight. The 'we will not do' list is as important as the 'we will'. The document is falsifiable — someone could disagree with specific sentences. Anti-patterns to avoid: bullet lists, slideware habits (fragments), aspirational TAM without grounding, strategy that is a list of features, 'we will do everything well' optimism, roadmaps disguised as strategy. Output in Markdown, structured as six numbered sections each with a clear heading, approximately six pages of prose total (~3,000–4,000 words depending on density).
User Message
Write an Amazon-style 6-pager. Product area: {&{PRODUCT_AREA}} Horizon (1 or 3 years): {&{HORIZON}} Team context: {&{TEAM}} Strategic question: {&{QUESTION}} Key data or interviews available: {&{EVIDENCE}}

About this prompt

Produces a complete Amazon-style 6-pager for product strategy: customer, problem, bets, architecture, GTM, and ask.

When to use this prompt

  • check_circlePMs writing a quarterly strategy narrative
  • check_circleFounders pitching a product line to the exec team
  • check_circleEngineering leads framing platform bets

Example output

smart_toySample response
## 1. Summary & Ask We propose three bets in billing automation over the next 12 months…
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.