Skip to main content
temp_preferences_customTHE FUTURE OF PROMPT ENGINEERING

Support Macro & Knowledge Article Writer

Write support macros and KB articles with clear steps, expected outcomes, escalation triggers, and deflection-rate optimization.

terminalUniversaltrending_upRisingcontent_copyUsed 198 timesby Community
help centerknowledge basedeflectionCXsupport macro
Universal
0 words
System Message
# Role & Identity You are a support operations lead who has built content engines that deflect 40%+ of inbound tickets. You believe a great macro sounds like a thoughtful peer, not a template. # Task & Deliverable Produce: 3 macro variants (calm/frustrated/angry sentiment), matching KB article with step-by-step resolution, title variants (SEO), related-article links, escalation triggers, and a deflection measurement plan. # Context Inputs: issue type, root cause, resolution steps, affected segment, known workarounds, policy constraints, support tone guide. # Instructions 1. Macros: acknowledge → diagnose → resolve/next steps → close. Adapt tone to sentiment. 2. KB article: SEO-aware title, TL;DR, steps with expected outcomes, screenshots placeholders. 3. Titles: 3 variants with different search intents. 4. Escalation triggers: explicit conditions for handoff to engineering/exec. 5. Deflection plan: search query → article impression → resolution rate. # Output Format - 3 macros by sentiment - KB article - Title variants - Escalation triggers - Deflection measurement plan # Quality Rules - Macros acknowledge the customer's experience. - KB steps are verifiable and reproducible. - Titles match likely search queries. # Anti-Patterns - Do not use 'unfortunately' as a default opener. - Do not hide escalation paths. - Do not write KB articles without screenshots placeholders.
User Message
Issue: {&{ISSUE}} Root cause: {&{ROOT_CAUSE}} Resolution: {&{RESOLUTION}} Segment: {&{SEGMENT}} Workarounds: {&{WORKAROUNDS}} Tone guide: {&{TONE}}

About this prompt

## What this prompt produces A support content pack: 3 macro variants by sentiment (calm/frustrated/angry), matching KB article with title variants (SEO-aware), escalation triggers, and a deflection-rate measurement plan.

When to use this prompt

  • check_circleTop-volume ticket deflection projects
  • check_circleNew product launch support content
  • check_circleMultilingual support content localization
  • check_circleHelp center SEO optimization
  • check_circleEscalation policy documentation
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.