Hire an AI feature beta launch planner

Everything it can hand back

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

• A launch plan with order, risks and rollback
• A beta programme: who, how many, how you hear from them
• The metrics decided before launch, with success, guardrails and the pull number
• Release notes in plain words, and a results read after launch

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: A feature is two weeks from done and nobody has planned the launch.

• Launch plan. Who gets the feature first, what could go wrong, the rollback and the dates.
• Beta plan. Who joins the beta, how many, how to invite them, weekly questions and when to close it.
• Metrics plan. Success targets, guardrail metrics that must not fall, and the number that would make you pull the feature.
• Release notes. Plain words on what changed for the user, why, and what to do if something looks different.
• Results read. Each metric against its target, what it means, what it cannot yet say, and keep, change or pull.
• HAND-BACK SUMMARY. Each step's file, any step not run and why, and every MISSING line in one list.

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 launch. Plans who gets the feature first, what could go wrong, the rollback and the dates.
• Set up the beta. Sets up the beta: who, how many, how to invite them and what to ask each week.
• Decide the metrics first. Decides success, guardrails and the pull number before anything ships.
• Run the beta. A pause. Run the beta. Collect the weekly feedback and fix what it finds.
• Write the release notes. Writes release notes in plain words about what changed for the user. You approve and publish.
• Launch and wait. A pause. Publish the release notes and roll out. After two to four weeks, paste the numbers.
• Read the numbers. Reads the post-launch numbers against the metrics you set and says what they mean and what they cannot yet say.

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 launch-a-feature-through-a-beta-and-read-the-numbers 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/launch-a-feature-through-a-beta-and-read-the-numbers/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

• The feature: what it does and who it is for
• How you can reach users and roll out to a subset
• What the business needs from this feature
• After launch, the numbers and the beta feedback

Helpful context (optional)

• Support tickets about the problem the feature solves
• Past launch results
• Your analytics event names

Tools and access

• Any good chat AI: Every step is a plan or a piece of writing.
• Your feature flag or rollout tool: Lets you show the feature to a subset and roll it back.
• Your analytics: The numbers for the results read come from here.

Functions and deliverables

• Feature beta launch planner: Share the feature, users and business goals. Get a beta plan, measures set before launch, release-note drafts and a later results review.
  • A launch plan with order, risks and rollback
  • A beta programme: who, how many, how you hear from them
  • The metrics decided before launch, with success, guardrails and the pull number
  • Release notes in plain words, and a results read after launch
• Feature launch planner: Plan a feature launch your whole team can follow. Get messaging, support prep, a staged rollout and rollback triggers for your feature.
  • A launch tier and task list
  • Messaging and support prep
  • A staged rollout plan
  • Metrics to track
  • Rollback triggers
  Source: RampStack.
• Beta program planner: Describe your launch. Get who to invite, what to ask them, and clear rules for when the beta ends.
  • A beta type and cohort size
  • Participant selection criteria
  • A feedback and triage plan
  • Ship, extend or stop rules
  Source: RampStack.
• Product metrics planner: Plan product metrics for your stage. Give it your product and goal. You get the KPIs to track, a dashboard layout and a read on retention.
  • A chosen metric framework
  • KPIs for your stage
  • A layered dashboard layout
  • A reading of retention and adoption
  Source: Alireza Rezvani.
• Release notes writer: Point it at your commits. Get tidy release notes and the right version bump from Conventional Commits.
  • Release notes grouped by type
  • Recommended version bump
  • Commit format check results
  • Output ready for a changelog file
  Source: Alireza Rezvani.
• Product metrics review writer: Turn your product numbers into a metrics review: a scorecard against targets, what moved, likely causes and next steps. Paste your figures to start.
  • A scorecard against targets
  • Trends and notable changes
  • Likely causes for spikes and drops
  • Recommended actions
  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

• A feature is two weeks from done and nobody has planned the launch.
• Your last launch went to everyone and broke something.
• Your team argues after launch about whether it worked.

Limits to check before starting

• You are fixing a bug or making a tiny change you cannot roll out to a subset: write a standard changelog line instead.
• Your feature targets onboarding drop-off: pair it with the New-user retention test planner workflow.
• You want to judge whether to build a feature at all: use the Feature request screener first.

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 every skill file this workflow uses.
• Give the folder to Claude (in Claude Code, or as files in a Claude Project) and say "Follow HANDOFF.md".
• Paste the feature and who it is for. It plans the launch, the beta and the metrics.
• Run the beta. Collect the feedback it asks for.
• Approve and publish the release notes. After two to four weeks, paste the numbers for the results read.

Read it as data

Read the complete role setup as JSON. Connect your AI to the AI Blocks MCP library and read aiblocks://roles/launch-a-feature-through-a-beta-and-read-the-numbers 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.