Hire an AI product event tracking and retention dashboard planner

Everything it can hand back

Your task sets the actual outputs. The specialist picks the methods that cover them.

• One main number to steer by and a list of events with clear names
• Funnels, sign-up groups and a version note for the plan
• A colour-coded retention grid with a plain reading of where people drop
• A page with cards, charts and filters you can open and share

How it does the job well

• Start from the user problem and the evidence for it, then the solution.
• Write decisions down with the reason and the options you rejected.
• Keep scope small enough to ship and learn. Name what is out of scope.
• Define how success will be measured before building.

Mistakes it avoids

• Treating opinions or one loud request as proven demand.
• Specs that skip edge cases, error states or dependencies.
• Roadmaps with dates but no owners or confidence levels.

How the work is checked

• Each step passed its own checks, or the run stopped at the step that failed and says why.
• The steps ran in order, and each one used the result of the one before.
• Nothing was invented to fill a gap. Every gap is a MISSING: line.
• Nothing was sent, published or paid for without a clear yes.
• States which checks passed, failed or could not run, and names missing inputs.

These checks have not been run against a model yet. Your AI uses them to check its own work.

Capabilities

• Plan the events. Picks one main number, lists events as object then past-tense action, separates event details from person details, and sets funnels and sign-up groups.
• Ship it and wait. Pause. You add the events to your product, let people use it for two to four weeks, and export sign-up and activity dates.
• Build the retention grid. Sets what counts as active, builds the group by week table from your export, works out the share still active, and draws a colour-coded grid with a plain reading.
• Build the dashboard. Puts the main number in cards, charts the grid and the funnel, adds filters for group and week, and saves one page you can share.

How the role works

1. Checks your task, context and available tools.
2. Picks the methods needed and prepares a work plan.
3. Carries out supported tasks, with each method's limits and review gates.
4. Checks the real deliverables and corrects supported faults.
5. Hands back files, evidence and unresolved gaps.

Your specialist's working setup

Download the base specialist without a task form or account. README.md and SETUP.md explain how to use the folder. SOUL.md defines its scope. INTAKE.md asks missing questions inside your AI. PLAYBOOK.md, SKILLS.md, BEST_PRACTICES.md, CHECKS.md and HANDOFF.md guide the work and its checked deliverables.

Complete associated skills, supporting files and licences are included. Choose only the methods needed for the actual task. Keep context, working files and accepted feedback in your AI project.

Use this specialist through MCP or the API

Call prepare_specialist with role_id set-up-product-tracking-and-build-a-retention-dashboard only. No task is required to load it. Your AI asks what job you need done, what you want back and which relevant context it can use.

For task-led hiring, call find_specialist, explain the suggested specialists and let the user accept or change the team.

Complete ZIP: Download base specialist. API: GET /api/v1/specialists/set-up-product-tracking-and-build-a-retention-dashboard/pack. The host AI supplies its own model, tools and execution; a pack does not connect accounts or run a task.

Inputs and helpful context

The specialist starts from the task brief. Only active methods require their inputs.

For the primary method, when used

• A plain description of your product and what a person does in it
• Which tool you use for tracking, if you have one (optional)
• After the pause, sign-up dates and activity dates for each person
• The audience for the dashboard (optional)

Functions and deliverables

• Product event tracking and retention dashboard planner: Describe your product and chosen retention measure. Get an event plan, cohort table and dashboard from real usage data when tools support it.
  • One main number to steer by and a list of events with clear names
  • Funnels, sign-up groups and a version note for the plan
  • A colour-coded retention grid with a plain reading of where people drop
  • A page with cards, charts and filters you can open and share
• Event tracking planner: Turn product steps and set goals into named actions, user rules, and a plan to track use.
  • Event list with names and properties
  • Naming and versioning rules
  • Funnel and retention definitions
  • User identity plan
  • North Star metric choice
  Source: RampStack.
• Retention heatmap maker: Give it signup and activity dates. Get retention by group over time, as a colour-coded grid with a plain reading.
  • A cohort by period retention table
  • A colour-coded heatmap
  • Retention curves for each group
  • A plain-English report of what it shows
  Source: Nimrod Fisher.
• Offline dashboard builder: Build a self-contained HTML dashboard from supplied data, with charts and filters that work offline.
  • Self contained HTML dashboard
  • KPI cards and charts
  • Working filters and tables
  • Steps to swap in real data
  Source: Anthropic.
• Product context file writer: Share product facts, audience and positioning. Get a reviewed context file that other marketing skills can reference.
  • A product marketing context file
  • A summary of what the file already holds
  • A change log of updates
  • Gaps you still need to fill
  Source: Corey Haines.

Tasks you can use it for

• You are about to add analytics to a new product or feature.
• Your current tracking is a mess and you want to start again with a clean plan.
• You want to know how many people come back and which sign-up group holds best.

Limits to check before starting

• You have only a handful of sign-ups so far: plan the tracking with step 1, then come back when you have a few hundred.

Best way to use this role

Give it one clear outcome, the actual files and a definition of done. Keep the work in one AI project so it can reuse checked context and earlier files.

• Download the handoff pack. It's a zip with HANDOFF.md and the 3 skill files in the order they run: Event tracking planner, Retention heatmap maker and Offline dashboard builder.
• Give the folder to Claude (in Claude Code, or as files in a Claude Project) and say "Follow HANDOFF.md".
• Describe your product and what counts as a person using it. Step 1 gives the event plan and stops.
• Pause. Ship the events, let real people use the product for two to four weeks, then export sign-up dates and activity dates per person.
• Attach the export. It builds the grid and then the dashboard.

Read it as data

Read the complete role setup as JSON. Connect your AI to the AI Blocks MCP library and read aiblocks://roles/set-up-product-tracking-and-build-a-retention-dashboard for its role instructions and pinned sources.

This is a prepared AI role. No task has run. Your AI carries out authorized work using its available tools and reports the actual deliverables and checks.