Synthesise across participants without counting repeated mentions as independent evidence; communicate decisions with their support.
AI PRODUCT PLAYBOOK
Don't prompt the process. Run the Activity.
Every Activity combines the right people, agents, context and quality gate, from customer evidence to shipped software.
Your team keeps the judgement. Teklens handles the coordination around it.
An Activity is a concrete step of product work, from the first source to human approval. It knows who owns the job, what context it needs, which agents and skills to use, what good looks like and where the result goes.
How the Playbook works
- Product Brain
- Playbook
- Activity
- Agents & Skills
- Outcome
- Human gate
Featured Activities
The clearest examples of context-aware, multiplayer product work.
- Strategy & DiscoverySD-06InputInterview recordsSkillsSynthesise supplied evidence · Record decisions and follow-up · Prepare task contextOutcomeFindings recap
- Strategy & DiscoverySD-12
Answer whether the opportunity deserves exploration without prematurely prescribing requirements or implementation.
InputProblem + evidence + goalsSkillsDraft a feature investment brief · Prepare task context · Review an artifact against agreed criteriaOutcomeFeature brief - Strategy & DiscoverySD-13
Prioritise by objective contribution without forcing essential maintenance into an invented strategic link.
InputBacklog + objectivesSkillsPrioritise against objectives · Prepare task context · Review an artifact against agreed criteriaOutcomeRanked, reasoned order - Define & DesignDD-06
Describe what users must be able to do, explicitly bound scope, and avoid substituting design or architecture for requirements.
InputProblem + direction + measuresSkillsDraft product requirements · Prepare task context · Review an artifact against agreed criteriaOutcomePRD - Define & DesignDD-08
Prepare and refine a PM-agreed subset of upcoming stories; preserve partial meeting coverage, per-story discussion and confirmation, and resume the same Activity without overwriting approved sources.
InputBacklog + horizon + notesSkillsPrepare an agreed refinement scope · Synthesise refinement decisions per story · Draft a Jira storyOutcomeRefined stories - Build & VerificationBV-01
Review actual change scope and system effects, separating substantiated issues from optional preferences.
InputDiff + ticketSkillsReview implementation against the ticket · Prepare task context · Review an artifact against agreed criteriaOutcomeReview verdict - Operate & LearnOL-01
Translate shipped changes into user value and never equate a merged change with general availability.
InputMerged changes + issuesSkillsCollect and write release notes · Prepare task context · Review an artifact against agreed criteriaOutcomeRelease notes - Operate & LearnOL-04
Learn from system conditions and information available at the time, preserving uncertainty and avoiding personal blame.
InputTimeline + accountsSkillsDraft a blameless incident postmortem · Synthesise supplied evidence · Prepare task contextOutcomePostmortem
All Activities
Start wherever the conversation has useful evidence. The steps are prompts for the Activity, not a required sequence, and «usually next» is a suggestion, not a mandatory step.
Strategy & Discovery
- How to write OKRs
- How to define and use KPIs
- Define product positioning
- User interviews — planning & prep
- User interviews — running the session
- User interviews — synthesis & distribution
- How to map a customer journey
- How to map an opportunity solution tree
- How to map and test assumptions
- How to use the Kano model
- How to prioritise using jobs-to-be-done
- How to write a feature brief
- How to prioritise against your objectives
- How to build a weighted scoring model
- How to prioritise with a 2×2 matrix
- How to run effective product meetings
- How to share product updates on Slack
- Coordinate a go-to-market launch
- How to run a retrospective
Define & Design
- How to define success metrics
- Success metrics with Discover, Use, Rely
- How to use RICE
- How to prioritise with ICE scoring
- How to prioritise with MoSCoW
- How to write a PRD
- How to write a good ticket
- How to run backlog refinement
- How to record an architecture decision
- How to define and review service level objectives
- How to run a design critique
- How to test a prototype with users
- Design onboarding to first value
- How to write error messages
- Run an adoption experiment
- How to run exploratory testing
Build & Verification
Choose the path that matches your role.
Set the Product AI direction with us, or test the shared Product Brain on real work with Jira and code.