Teklens logo
DEEN
Back to the Playbook
BuildQualityBU-03

Review implementation against intent

Catch drift between the original product decision, the story and the delivered code before it reaches production.

Product statusAvailable now

Context in4 required inputsPRD and Jira story · Acceptance criteria · Pull request or current code
TransformationQA + QA Agent + Architecture AgentCode Analysis · Atlassian · Local Files
OutcomeAlignment review with pass or fail per requirement, deviations and recommended corrections.Artifact: Jira story

Why it matters

Did what we decided survive implementation? Decision, spec, Jira story and pull request are compared by an assigned agent; a named person approves or requests changes.

Owner

QA

Human + Agent

Participants · Agents

Product ManagerEngineerQA AgentArchitecture Agent

Trigger

Event-drivenA pull request is ready for review, or a merged implementation is available.

Required context

JiraPRD and Jira storyJiraAcceptance criteriaCodePull request or current codeProduct BrainRelevant decisions

Optional context

Design systemUI draftArchitectureArchitecture decisionCodeTest results and coverage

Skills

Code AnalysisAtlassianLocal Files

Methods used inside this Activity: Spec conformance check · Test-impact analysis of risky areas

Activity steps

  1. 1Summarise the change and compare it with intent, story and acceptance criteria.
  2. 2Inspect the affected code and the test coverage of risky areas.
  3. 3Identify deviations and distinguish intentional change from defect.
  4. 4Propose corrections or a context update.

Output

Alignment review with pass or fail per requirement, deviations and recommended corrections.

Artifacts

Updates: Jira story, Product Brain

What good looks like

  • Every deviation links to a requirement or an approved decision.
  • Intentional change is separated from defect.
  • Coverage gaps in risky areas are named.
  • The verdict is explicit.

Quality gate

A named reviewer approves material scope changes or release blockers.

Destination

GitHubJiraProduct Brain

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.

Book a demoBack to the Playbook