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

  1. Product Brain
  2. Playbook
  3. Activity
  4. Agents & Skills
  5. Outcome
  6. Human gate
8 Activities

Featured Activities

The clearest examples of context-aware, multiplayer product work.

  • Strategy & DiscoverySD-06

    Synthesise across participants without counting repeated mentions as independent evidence; communicate decisions with their support.

    InputInterview records
    SkillsSynthesise supplied evidence · Record decisions and follow-up · Prepare task context
    OutcomeFindings recap
    Result onlyHuman gate
  • Strategy & DiscoverySD-12

    Answer whether the opportunity deserves exploration without prematurely prescribing requirements or implementation.

    InputProblem + evidence + goals
    SkillsDraft a feature investment brief · Prepare task context · Review an artifact against agreed criteria
    OutcomeFeature brief
    Feature briefHuman gate
  • Strategy & DiscoverySD-13

    Prioritise by objective contribution without forcing essential maintenance into an invented strategic link.

    InputBacklog + objectives
    SkillsPrioritise against objectives · Prepare task context · Review an artifact against agreed criteria
    OutcomeRanked, reasoned order
    Objective alignmentHuman gate
  • Define & DesignDD-06

    Describe what users must be able to do, explicitly bound scope, and avoid substituting design or architecture for requirements.

    InputProblem + direction + measures
    SkillsDraft product requirements · Prepare task context · Review an artifact against agreed criteria
    OutcomePRD
    PRDHuman gate
  • 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 + notes
    SkillsPrepare an agreed refinement scope · Synthesise refinement decisions per story · Draft a Jira story
    OutcomeRefined stories
    Refinement scopeHuman gate
  • Build & VerificationBV-01

    Review actual change scope and system effects, separating substantiated issues from optional preferences.

    InputDiff + ticket
    SkillsReview implementation against the ticket · Prepare task context · Review an artifact against agreed criteria
    OutcomeReview verdict
    Result onlyHuman gate
  • Operate & LearnOL-01

    Translate shipped changes into user value and never equate a merged change with general availability.

    InputMerged changes + issues
    SkillsCollect and write release notes · Prepare task context · Review an artifact against agreed criteria
    OutcomeRelease notes
    Release notesHuman gate
  • Operate & LearnOL-04

    Learn from system conditions and information available at the time, preserving uncertainty and avoiding personal blame.

    InputTimeline + accounts
    SkillsDraft a blameless incident postmortem · Synthesise supplied evidence · Prepare task context
    OutcomePostmortem
    Incident postmortemHuman gate

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.

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.