Back to the Playbook
DefinePlanningDE-11

Prepare refinement

Walk into refinement with the right stories, evidence, dependencies and open decisions already assembled, so the session is spent on decisions, not on searching.

Product statusAvailable now

Context in4 required inputsCandidate backlog · Current objectives · Parent epics and decisions
TransformationProduct Manager + Product Agent + Architecture AgentAtlassian · Code Analysis · Estimate Feature · Local Files
OutcomeRefinement pack with a recommended story set and proposed story updates.Artifact: Jira story

Why it matters

The multiplayer example: Jira, objectives, customer evidence and code come together before the meeting. People and agents work from the same Product Brain; the team decides.

Owner

Product Manager

Human + Agent

Participants · Agents

EngineerProduct AgentArchitecture Agent

Trigger

ScheduledBefore a scheduled refinement session.

Required context

JiraCandidate backlogProduct BrainCurrent objectivesProduct BrainParent epics and decisionsCodeRelevant code and architecture

Optional context

Customer evidenceCustomer evidenceJiraEstimatesJiraPrior discussionJiraImplementation plans

Skills

AtlassianCode AnalysisEstimate FeatureLocal Files

Methods used inside this Activity: Definition of Ready check · Readiness score per story

Activity steps

  1. 1Select candidate stories against the objectives and the session capacity.
  2. 2Check each story for completeness and readiness.
  3. 3Gather evidence, estimates and dependencies from Jira and the code.
  4. 4Flag risks and list the decisions the team must make.
  5. 5Propose story updates for review.

Output

Refinement pack with a recommended story set and proposed story updates.

Artifacts

Updates: Jira story

What good looks like

  • Every candidate has clear intent and a readiness status.
  • Unknowns and dependencies are surfaced before the meeting.
  • Scope fits the session.
  • Proposed changes are marked as proposals.

Quality gate

The product manager reviews proposed story changes before they reach Jira.

Destination

Teklens onlyJira

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.