Back to the Playbook
DiscoverDI-06
Investigate current product behaviour
Explain how an existing capability actually works today, from the code, before changing, extending or documenting it.
Product statusAvailable now
Context in3 required inputsThe question to answer · Relevant product area · Codebase
TransformationProduct Manager + Product Agent + Architecture AgentCode Analysis · Atlassian · Local Files · Find Code Owners
OutcomeCurrent-state analysis with affected components, owners and stale documentation.Artifact: Architecture context
Why it matters
New product managers take months to learn what the product really does. This Activity answers the question in the code, with the components and the people who know them.
Owner
Product Manager
Human + Agent
Participants · Agents
EngineerProduct AgentArchitecture Agent
Trigger
A feature change, unclear behaviour, a customer question or discovery work touching existing functionality.
Required context
FilesThe question to answerProduct BrainRelevant product areaCodeCodebase
Optional context
JiraJira historyArchitectureArchitecture notesConfluenceUser documentation
Skills
Code AnalysisAtlassianLocal FilesFind Code Owners
Activity steps
- 1Trace the relevant code paths.
- 2Identify components, dependencies and the people who know them.
- 3Compare actual behaviour with documentation and tickets.
- 4Summarise behaviour, constraints and unknowns.
Output
Current-state analysis with affected components, owners and stale documentation.
Artifacts
Updates: Architecture context
What good looks like
- Grounded in current code.
- Fact is separated from inference.
- Dependencies and owners are named.
- Stale documentation is flagged.
Quality gate
No human gate before the result is promoted. It stays an Activity result in Teklens until a person decides to use it.
Destination
Teklens onlyProduct 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.
- Build your own company brain: the enterprise AI playbook from Stripe's engineering team
- PM to engineer ratio: why a CPO regrets product management – and still hires PMs
- The best AI product management books in 2026
- Why Spotify's product management won't work for your business – even less so with AI agents
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.