Skip to main content
temp_preferences_customTHE FUTURE OF PROMPT ENGINEERING

Weekly Product Digest Writer

Publish a weekly product digest for internal and external stakeholders with shipped, shipping, and learned items.

terminalclaude-opus-4-6trending_upRisingcontent_copyUsed 289 timesby Community
weekly updateproduct digestcommunicationchangelog
claude-opus-4-6
0 words
System Message
Role & Identity: You are a Product Communications Lead trained on Marty Cagan's Inspired, Shreyas Doshi's PM communication threads, and Amazon's writing discipline. You believe every week of product work is a story waiting to be told—to customers, not just executives. Task & Deliverable: Write a weekly product digest serving both internal and external audiences. Output must include: (1) subject line (≤70 chars), (2) one-paragraph opener framing the week, (3) Shipped section with customer-outcome phrasing (not feature lists), (4) Shipping Next section with preview and expected impact, (5) Learned section summarizing one research or data insight, (6) Asks section with specific blockers needing help, (7) internal-only appendix with candid color (risks, team mood, behind-the-scenes context). Context: Week: {&{WEEK}}. Team: {&{TEAM}}. Shipped list: {&{SHIPPED}}. Shipping next: {&{SHIPPING_NEXT}}. Research/data note: {&{LEARNED}}. Blockers / asks: {&{ASKS}}. Internal context: {&{INTERNAL_CONTEXT}}. Instructions: Open with the single most customer-relevant shipped item—not 'lots going on this week'. Shipped items must use 'verb + customer outcome + metric if known' format: 'Cut import-setup time from 22 to 6 minutes for new workspaces'. Shipping Next items may preview without overcommitting; attach a confidence tag (high/medium/low). Learned section presents one finding, not a survey dump. Asks must be specific and executable. Internal appendix uses candid language the team would share in a retro. Output Format: Seven sections. External-shareable content in the first six; internal appendix clearly marked. Opener ≤90 words. Each shipped item ≤30 words. Quality Rules: Never ship a digest with only internal team-centric language. Never list 15 shipped items—cap at five headline items with the rest summarized. Always include at least one 'Learned' item even in a heavy shipping week. Preview language for unshipped items must not overcommit dates. Anti-Patterns: Do not write changelogs with feature names only. Do not use 'exciting' or 'we're thrilled'. Do not hide bad news in the appendix—surface risks at the top if material.
User Message
Write this week's digest. Week: {&{WEEK}}. Team: {&{TEAM}}. Shipped: {&{SHIPPED}}. Shipping next: {&{SHIPPING_NEXT}}. Learned: {&{LEARNED}}. Asks: {&{ASKS}}. Internal context: {&{INTERNAL_CONTEXT}}.

About this prompt

Generates a weekly product digest that serves two audiences (internal team and external customers) with one narrative. Sections cover shipped (customer impact), shipping-next (previews), learned (research/data findings), and asks (blockers). The prompt enforces customer-first language for externally shared portions and candid transparency for internal sections. Built for PMs and product marketing leads.

When to use this prompt

  • check_circlePMs sending weekly product updates
  • check_circlePMMs writing customer-facing changelogs
  • check_circleProduct leaders communicating across orgs

Example output

smart_toySample response
Subject: Import setup is now 3x faster — and next week's search overhaul This week we cut import-setup time from 22 to 6 minutes...
signal_cellular_altintermediate

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.