Hire an AI growth channel experiment tracker

Everything it can hand back

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

• A recommendation with its evidence and missing facts
• A small test with an owner, cost cap and decision rule
• The next action and what needs approval

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.

What a good result looks like

An example, not your task: You need a practical way to find customers for a software business.

• business-profile.md. Your verified facts about the product, buyer and limits, with gaps marked MISSING.
• channel-matrix.csv. The channels considered, how well each fits your buyer, and why.
• experiments/. One plan per test, with an owner, a cost cap and a decision rule.
• results-ledger.csv. Each test's results, with the cohort and date window they cover.
• decision-log.md. The dated decision: focus, revise, stop or wait, with reasons, pending approvals and one next action.

How the work is checked

• Every requirement can be tested.
• Assumptions and risks are listed with how each will be checked.
• Dependencies and owners are named.
• 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 Al Ries would. This is a way of reviewing the work. It does not mean they wrote or endorse it.

Capabilities

• Read your facts. Uses public product pages and your own facts. Labels anything it could not check.
• Design the test. Matches the channel to the buyer and writes a small, measurable test.
• Make the decision. Sets what would justify continuing, changing the test or stopping. Results stay pending until there is evidence.

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 traction-experiment-keeper 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/traction-experiment-keeper/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 public product link or pasted product and pricing text
• Your growth goal, stage and buyer, if known
• Cash and time limits, past tests and results, if available

Functions and deliverables

• Growth channel experiment tracker: Track channel test plans and mature results. Get a focus, revise, stop or wait decision with a bounded next step.
  • A recommendation with its evidence and missing facts
  • A small test with an owner, cost cap and decision rule
  • The next action and what needs approval
• SaaS growth channel test planner: Compare 19 ways to reach software customers. Plan small tests and review actual use, payments, retention and costs before choosing one.
  • A recommendation with its evidence and missing facts
  • A small test with an owner, cost cap and decision rule
  • The next action and what needs approval
• Customer acquisition experiment reviewer: Share your test results. Get a checked comparison and a focus, revise, stop or wait decision.
  • A results ledger with costs, leads, trials and paid customers checked
  • A review of definitions, data quality and credit for each sale
  • A verdict (focus, revise, stop or wait) and the next small test with its limits
• Growth channel profile builder: Turn your product link into a business profile with your buyer, offer, growth goal and missing facts, ready for a small channel test.
  • A business-profile.md with your buyer, offer, goal, limits and the evidence behind each fact
  • A list of the private facts still missing
  • The limits a later test needs (cash cap, hours, owner, tracking), ready for the channel ranker to design the test
• 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.
• Al Ries: Clarify what a brand should stand for using Al Ries’s recorded approach. Examine its category, focus, name and launch story.
  • Your problem worked on the way Al Ries would: their questions, their method, their push-back
  • The answer or the work, in Al Ries'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

• You need a practical way to find customers for a software business.
• You want to test a growth idea before committing more time or money.

Limits to check before starting

• You have no traffic or buyer conversations yet: talk to ten likely buyers first, then come back with what they said.
• You sell something other than software: use a plain channel plan for your own kind of business, or ask a marketing adviser.
• You want the AI to send messages, spend money or start a schedule on its own: it will not. You approve each action yourself.

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.

• Add the agent and both companion skills (Find your SaaS growth channel and Traction experiment result reviewer) to your AI. It needs both.
• First run: paste your product URL and any facts you already know, such as your goal, buyer, cash and time limits.
• Later runs: attach the saved folder (business-profile.md, results-ledger.csv, decision-log.md) and add the new results with their dates.
• Review the plan and the decision. Approve any send, spend or booking yourself.

Read it as data

Read the complete role setup as JSON. Connect your AI to the AI Blocks MCP library and read aiblocks://roles/traction-experiment-keeper 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.