Back to the Playbook
DiscoverEvidenceDI-05

Analyse customer feedback

Turn support tickets, requests and qualitative feedback into clustered product signals with evidence, so loud customers are not mistaken for broad demand.

Product statusAvailable now

Context in3 required inputsCustomer feedback and support content · Customer and account metadata · Existing opportunities
TransformationProduct Manager + Product AgentLocal Files · Atlassian · Code Analysis
OutcomeFeedback clusters with evidence, frequency and recommended follow-up.Artifact: Opportunity

Owner

Product Manager

Agent-led

Participants · Agents

EngineerProduct Agent

Trigger

ScheduledA scheduled feedback review, new feedback arriving, or a spike in related requests.

Required context

Customer evidenceCustomer feedback and support contentFilesCustomer and account metadataProduct BrainExisting opportunities

Optional context

AnalyticsUsage dataCustomer evidenceInterview researchProduct BrainCurrent objectivesCodeRelated code and components

Skills

Local FilesAtlassianCode Analysis

Activity steps

  1. 1Collect and deduplicate the feedback.
  2. 2Cluster by problem and affected users, separating symptom from cause.
  3. 3Link clusters to existing tickets, opportunities and components.
  4. 4Recommend a follow-up per cluster.

Output

Feedback clusters with evidence, frequency and recommended follow-up.

Artifacts

Updates: Opportunity, Product Brain

What good looks like

  • Duplicates are merged.
  • Evidence is retained per cluster.
  • Frequency and severity are separated.
  • Clusters are linked to existing work.

Quality gate

The product manager validates which clusters become opportunities.

Destination

Product BrainJira

Usually next

People and agents work from the same Product Brain. The owner stays accountable. Assigned agents prepare and check. A named person approves at the gate.

Deep dives from the AI PM Lab

Articles that explain the thinking behind this Activity.

Show us exactly how product work happens today.

Thirty minutes with a founder. We compare your process with the Playbook and pick the first Activity to run on your Jira and your repo.