The Fortune 100 AI Prompt Library™

    Retrospective Pattern Analysis

    Look across retrospectives to find recurring issues, not just the problem from the last sprint.

    Free · No signup required · For Claude or ChatGPT

    Explore all 29 workflows
    1. Product & EngSome setupClaude + ChatGPT

      Retrospective Pattern Analysis

      Look across retrospectives to find recurring issues, not just the problem from the last sprint.

      What you'll need

      • Retrospective notes (multiple sprints)
      • Sprint metrics (velocity, completion rate)
      • Team composition changes
      • Project/initiative context

      Put it to work

      Save these instructions in a Claude Skill or Project, or in a ChatGPT Project or Custom GPT. Add your context, run the sample prompt, and check the result against your team's standards before anyone relies on it.

      Reusable playbook

      Learn the method, adapt the details, then put it to work.

      1Understand the method2Replace the placeholders3Copy, run, and review

      Start here

      Reusable instruction — Claude: save as a skill file at ~/.claude/skills/product/retro-analysis.md · ChatGPT: paste into a Custom GPT's instructions or a Project.

      01

      Give the AI a clear role

      You are an agile coach who identifies patterns and actionable improvements from retrospective data.

      02

      Bring the right context

      • {{metrics_path}} - Sprint metrics (velocity, completion rate) (optional)
      • {{team_path}} - Team composition information (optional)
      What you provide
      • Retrospective notes (multiple sprints)
      • Sprint metrics (velocity, completion rate)
      • Team composition changes
      • Project/initiative context
      03

      Run the method

      Given retrospective data across multiple sprints
      1. 1

        Pattern Recognition

        • Recurring themes (what keeps coming up)
        • Improvement trajectories (what's getting better/worse)
        • Category clustering (process, people, tools, external)
      1. 1

        Root Cause Analysis

        • Why do certain issues persist?
        • What's preventing improvement?
        • Systemic vs. situational issues
      1. 1

        Correlation Analysis

        • Issues vs. velocity impact
        • Team health vs. delivery
        • Changes vs. outcomes
      1. 1

        Recommendations

        • Experiments to try
        • Metrics to track
        • Accountability mechanisms
      04Preview the deliverableSee the shape of a strong answer before you run the workflow.
      Retrospective Analysis

      Period: [Sprints analyzed] Team: [Team name] Sprints Analyzed: [Count]

      Pattern Summary
      Theme
      Unclear requirements
      Frequency
      6/8 sprints
      Trend
      Stable
      Category
      Process
      Severity
      High
      Theme
      Deploy friction
      Frequency
      4/8 sprints
      Trend
      Increasing
      Category
      Tools
      Severity
      Medium
      Deep Dive: Persistent Issues
      Issue 1: Unclear Requirements (75% of sprints)

      Evidence:

      • Sprint 1: "Stories lacked acceptance criteria"
      • Sprint 3: "Had to re-clarify mid-sprint"
      • Sprint 6: "Scope creep due to ambiguity"
      • Sprint 8: "Multiple interpretations of done"

      Root Cause Analysis: [Analysis of why this persists]

      Velocity Impact: Estimated 15-20% velocity loss per sprint

      Attempted Fixes:

      • Sprint 2: Added AC template (partially effective)
      • Sprint 5: PM review meeting (not sustained)

      Recommended Experiment:

      • What: [Specific intervention]
      • Measure: [How to track success]
      • Duration: [How long to try]
      • Owner: [Who drives this]
      What's Improving
      Theme
      Code review speed
      Trend
      Decreasing complaints
      Evidence
      3→0 mentions over 4 sprints
      What's Degrading
      Theme
      On-call burden
      Trend
      Increasing
      Risk
      Burnout risk
      Correlation Insights
      • Sprints with unclear requirements had 23% lower completion rates
      • Sprints after holidays showed 2-3 day "ramp-up" pattern
      • [Other correlations]
      Recommended Actions
      Priority
      P1
      Action
      [Action]
      Owner
      [Name]
      Timeframe
      [When]
      Success Metric
      [Metric]
      Priority
      P2
      Action
      [Action]
      Owner
      [Name]
      Timeframe
      [When]
      Success Metric
      [Metric]
      Retro Health Check
      • Participation rate: [X]%
      • Action item completion: [Y]%
      • Sentiment trend: [Improving/Stable/Declining]

      Try this prompt

      Analyze our last 6 sprint retros:

Sprint 1: Too many meetings, unclear requirements, good collaboration
Sprint 2: Deploy took 2 days, unclear requirements, new dev onboarding went well
Sprint 3: Scope creep, CI pipeline broke twice, team morale good
Sprint 4: Unclear requirements (again), technical debt slowing us down
Sprint 5: On-call was brutal, too much WIP, shipped the big feature
Sprint 6: Still dealing with tech debt, requirements are getting better, team is tired

What systemic issues should we address, and what experiments do you recommend?

      Before you trust the output

      • Track action item completion (are we following through?)
      • Look for root causes, not just symptoms
      • Celebrate improvements to motivate continued reflection

      Your next step

      Want this workflow to run reliably every week?

      Bring Retrospective Pattern Analysis to our free live workshop. We'll show you how to turn the reusable instructions into a working AI Agent Skill—without writing code.

      Bring This Workflow