Hire an AI product funnel steps and experiment review

Everything it can hand back

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

• A tracking plan with steps, groups, one main metric and the input metrics you control
• Conversion per step against its normal swing, with real moves marked
• Each sign-up week's path beside the changes that moved it
• A verdict on any experiment that reached its read date
• The cause behind a repeated loss, or "unknown" with the fact that would settle it
• One experiment with one change, one rate and a read date

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

• Calling a move inside the normal swing a result.
• Reading an all-users average when a group chart exists.
• Planning two experiments on one step.
• Changing the tracking plan to make a chart look better.
• Treating opinions or one loud request as proven demand.
• Specs that skip edge cases, error states or dependencies.

What a good result looks like

An example, not your task: Your product tracks events and the weekly review is a dashboard and a debate.

• This week. The main metric against last week, the inputs you control, and how many steps moved past their normal swing.
• The funnel. Conversion per step, last week's rate, the normal swing, and a mark for noise or a real move.
• The groups. Each sign-up week's path through the steps, beside the change that shipped that week.
• Experiments read. Any experiment that reached its read date, with its rate, the move expected, the move seen and a verdict.
• The cause. The chain of whys and the fixable cause, or unknown with the fact that would settle it.
• One experiment. One change, the rate it should move, who gets it and the date to read it.

How the work is checked

• Every rate comes from the plan's steps and the export, and groups are read as groups.
• Every move is compared with the step's normal swing before it is called a move.
• A cause was sought only when a step moved past its swing or lost the most two weeks running.
• At most one experiment was proposed, with one change and one rate.
• 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.

A second opinion

Before it hands back, your AI reviews the draft the way Eric Ries and Jeff Bezos would. This is a way of reviewing the work. It does not mean they wrote or endorse it.

Capabilities

• Build the plan once. Sets the events, steps, groups and main metric, marks the vanity numbers and picks the inputs you control.
• Log what changed. Adds last week's releases, campaigns and outages to a dated log, because a move with no change behind it is a mystery.
• Read the funnel. Conversion per step and the change, each compared with the step's normal swing from the last six weeks.
• Read the groups. Each sign-up week's path beside the changes log, so a change shows in the group that got it.
• Decide. A quiet week reports inputs against output and stops. A move past the swing or a repeated loss goes on to a cause.
• Find the cause. A chain of whys checked against the facts, ending in a fixable cause or an honest unknown.
• Plan one experiment. One change, the rate it should move, who gets it and the date to read it.
• Log and hand back. Adds the week's row and stops for your yes.

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 weekly-product-funnel-watcher 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/weekly-product-funnel-watcher/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

• Last week's event log or per-step counts with user id, event, time and sign-up date
• The numbers your team reports today (advised)
• What changed last week, with dates (advised)
• Your tracking plan and experiment log, once they exist

Helpful context (optional)

• Your release notes for the week, with dates
• Support tickets that mention a step in the funnel

Tools and access

• Claude Code: It can keep the plan, weeks, changes and experiments files between weeks and run every Monday.
• Your product analytics tool: Export events with user id, event name, time and sign-up date. Any tool that exports a CSV will do.
• Any good chat AI: Reading a table and writing the verdict is text work.
• A spreadsheet or analytics tool: Builds the group table from an export.
• Any good chat AI: Reading a sheet and writing formulas is text work.
• A spreadsheet or analytics tool: Builds the per-group tables and charts from your export.
• Any good chat AI: Tracing causes from a table of results is text and number work any strong chat AI does well with this skill.
• Any good chat AI: Building and checking a chain from records is text work. Claude, ChatGPT and Gemini all do it with this skill.
• Your ticket or incident system: Holds the logs and tickets the chain needs as proof. Copy in the lines that matter.
• Any good chat AI: Listing factors and mapping results is text work any strong chat AI does well with this skill.
• A spreadsheet: Keeps the held-fixed list and the results side by side for each run.

Functions and deliverables

• Product funnel steps and experiment review: Review where user progress drops. Compare sign-up groups, keep causes as hypotheses and propose one experiment for the weak step.
  • A tracking plan with steps, groups, one main metric and the input metrics you control
  • Conversion per step against its normal swing, with real moves marked
  • Each sign-up week's path beside the changes that moved it
  • A verdict on any experiment that reached its read date
  • The cause behind a repeated loss, or "unknown" with the fact that would settle it
  • One experiment with one change, one rate and a read date
• 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.
• Conversion funnel analyst: Find where people leave your sign-up or checkout funnel. Give it an event log and your steps to get conversion per step and ranked fixes.
  • Conversion per step
  • Drop-off counts
  • Time between steps
  • Segment comparison
  • Ranked fixes
  Source: Nimrod Fisher.
• Cohort funnel analyst: Read your results by join week or month. See which changes moved which rates, and whether the report can be trusted.
  • A table of each group's path
  • Which changes moved which rates, and which are unproven
  • Signs that you are stuck
  • A pass or fail on whether the report can be trusted
• Business metric quality reviewer: Find the vanity metrics in your weekly report and swap them for per-customer rates you can act on, plus one main number to track.
  • A table showing which numbers are vanity
  • Replacement rates with formulas
  • Results split by group and release
  • One goal, one main number and a data check
• Business activity metric planner: Pick input metrics you control from the numbers you report. Get three to six inputs, a proxy test for each and one output to check them.
  • Outputs listed and traced to inputs
  • Three to six input metrics that touch the customer
  • A proxy test for each, with a guard where needed
  • One output kept as a check
  • An owner, target and review date for each input
• Root cause finder: Find the root cause of a problem that keeps coming back. Get a chain of whys checked against facts, a fix and a prevention check.
  • The problem written as something seen, not a guess
  • A chain of whys, each answer with its proof or marked unconfirmed
  • A second chain, in case there is another cause
  • The root cause your team can change
  • A fix that removes it, and a prevention check
• One-change experiment planner: Plan a one-change experiment. Tell it what you want to learn and get a test plan that changes one thing and says what each result means.
  • The question rewritten in plain terms, with each term defined
  • The one change to test and the list of things held fixed
  • A second check, the no-effect result and what each outcome means
• 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.
• Eric Ries: Turn a product plan into testable guesses using Eric Ries’s public approach. Start with the riskiest assumption and measure what customers actually do.
  • Your problem worked on the way Eric Ries would: their questions, their method, their push-back
  • The answer or the work, in Eric Ries's voice, using their ideas by name
  • Anything that goes beyond their public record, marked
  • One suggested next step
• Jeff Bezos: Review a product or stuck decision through Jeff Bezos’s recorded approach. Start with the customer, test what can be undone and write the reasoning.
  • Your problem worked on the way Jeff Bezos would: their questions, their method, their push-back
  • The answer or the work, in Jeff Bezos's voice, using their ideas by name
  • Anything that goes beyond their public record, marked
  • One suggested next step

Tasks you can use it for

• Your product tracks events and the weekly review is a dashboard and a debate.
• A rate moved and nobody can say which of last week's three changes did it.
• You report numbers that only go up and want the ones that show cause.

Limits to check before starting

• Your product has no event tracking yet: set up a simple event list first, or review a plain dashboard with your team.
• Fewer than about 200 users reach the funnel each week: read two weeks together by hand, since one week swings too much.
• An experiment just ended and you want the full result: use the Experiment plan and results reviewer.

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.

• Start a chat with the agent. In Claude Code, add it as a skill or save it in .claude/agents, then ask it to run this week.
• Export last week's events in the same shape each week. Put the file in one folder, or attach it in the chat.
• On the first run, describe the product and the numbers you report. Approve the tracking plan it builds.
• Each week, paste what changed, with dates. Read the funnel and the one experiment. Run the experiment you agree with in your own tools.
• Run it again next Monday. It reads the new groups and judges any experiment that is due.

Read it as data

Read the complete role setup as JSON. Connect your AI to the AI Blocks MCP library and read aiblocks://roles/weekly-product-funnel-watcher 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.