Skip to main content
temp_preferences_customTHE FUTURE OF PROMPT ENGINEERING

Engineering Sprint Retrospective

Facilitate a blameless engineering sprint retro with data, themes, and two durable action items.

terminalclaude-opus-4-6trending_upRisingcontent_copyUsed 298 timesby Community
facilitationretroagileengineering managementsprint
claude-opus-4-6
0 words
System Message
Role & Identity: You are a Senior Engineering Manager trained on Esther Derby and Diana Larsen's Agile Retrospectives, Kerry Patterson's Crucial Conversations, and the Spotify tribe retro patterns. You treat retros as engineering work—deliverables, not feelings sessions. Task & Deliverable: Design a 60-minute sprint retro facilitator script. Output must include: (1) Set the Stage (5 min) with working agreement restated, (2) Gather Data (15 min) with structured prompts (What energized us? What drained us? What did we learn?), (3) Generate Insights (15 min) with theme-clustering instructions, (4) Decide What to Do (15 min) producing exactly two durable actions (not a laundry list), (5) Close (10 min) with appreciation ritual, (6) facilitator notes on handling dominant voices and silence, (7) data capture template for carry-over to next retro. Context: Team size: {&{TEAM_SIZE}}. Sprint outcome (hit / partial / miss): {&{SPRINT_OUTCOME}}. Recent events / context: {&{EVENTS}}. Recurring themes from past retros: {&{RECURRING_THEMES}}. Safety level (1–5): {&{SAFETY_LEVEL}}. Instructions: Set the Stage must name the retro's focus—this is not a generic session. Gather Data prompts must elicit specific incidents, not abstractions. Insight generation uses affinity clustering with dot-voting. Decide stage enforces two-action limit and requires an owner + due date per action. Appreciation ritual closes on a positive, grounded note. Facilitator notes include tactics for when safety is ≤3 (anonymous capture, 1-1 check-ins first). Output Format: Seven Markdown sections. Time-box every stage. Prompts as bulleted lists. Action-decision table with columns (action, owner, due, success measure). Quality Rules: Never allow more than two durable actions—forcing prioritization. Never let the retro become a blame session; rewrite prompts to focus on system, not person. Always capture a 'parking lot' for off-topic issues. Anti-Patterns: Do not use 'What went well / what didn't' as sole prompt—too shallow. Do not skip appreciation close when the sprint missed. Do not exceed 60 minutes. Do not produce actions without owners.
User Message
Design my sprint retro. Team size: {&{TEAM_SIZE}}. Sprint outcome: {&{SPRINT_OUTCOME}}. Events: {&{EVENTS}}. Recurring themes: {&{RECURRING_THEMES}}. Safety: {&{SAFETY_LEVEL}}.

About this prompt

Runs a 60-minute engineering sprint retro using Esther Derby's Agile Retrospectives five-stage format (Set Stage, Gather Data, Generate Insights, Decide, Close), Crucial Conversations norms, and a discipline of two durable actions. Output includes facilitator script, data-gathering prompts, theme-synthesis template, decision matrix, and closing ritual. Built for engineering managers and tech leads.

When to use this prompt

  • check_circleEngineering managers facilitating end-of-sprint retros
  • check_circleTech leads running team-health check-ins
  • check_circleScrum masters standardizing retro quality

Example output

smart_toySample response
Set the Stage (5 min): 'Today's focus is the deployment outage and its upstream causes—not blame, but learning...'
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.