Hire an AI small product launch planner

Everything it can hand back

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

• A smaller launch for the same date, with the core first, a ranked list and a later list of what was cut
• A teaser, preview and launch plan, with a sign-up page, a handful of insiders, a free sample and the launch message
• A ruling of yes, later or no on each request, with the full cost of every yes and a short reply for the customer

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 launch is running late or has grown too big, and the date matters more than the extras.

• Step 1: Smaller launch. The fixed date and budget, the heart of the product, the ranked launch list, the later list and a promise check.
• Step 2: Teaser and launch plan. Hints and sign-up page, insiders, preview, promo site, free sample and the launch message to your list.
• Step 3: Request screen. Each request with repeats from different people, hidden costs, a yes, later or no ruling and a short reply.
• 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.

A second opinion

Before it hands back, your AI reviews the draft the way Jason Fried would. This is a way of reviewing the work. It does not mean they wrote or endorse it.

Capabilities

• Cut the scope. Locks the date and budget, names the heart of the product and cuts the list in half until the core remains. Parks the rest and checks the launch promise.
• Plan the teaser and launch. Works back from the date, using the smaller plan from step 1. Plans hints and a sign-up page, a preview for a few insiders, a free sample and the message to your list.
• Screen the requests. Checks each request against the smaller plan and the teaser plan, and answers every one with not now. Counts repeats from different people, lists hidden costs and rules yes, later or no.

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 smaller-product-launch 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/smaller-product-launch/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

• Your launch plan with the full feature list
• Your launch date and budget, which the workflow treats as fixed
• Feature requests from customers, such as reviews or messages (optional)
• Your brand file, for the teaser and the preview (optional)

Helpful context (optional)

• A full list of feature requests, with who asked
• Your brand file, with your voice and offer
• A short list of people who would like an early look

Tools and access

• Any good chat AI: Holds the plan, the requests and the launch dates in one run.
• An email list tool: Collects sign-ups from the teaser page and sends the launch message.
• Any good chat AI: Ranking and cutting a list against one rule is text work.
• A shared task board: Moving cut items to a Later column keeps them parked, not lost.
• Any good chat AI: Planning stages and drafting page specs and messages is text work.
• An email list tool: Collects sign-ups and sends the launch message to the list.
• Any good chat AI: Counting, costing and drafting short replies is text work.
• Your support inbox or feedback tool: Real request counts come from there.

Functions and deliverables

• Small product launch planner: Share your launch goal, date and budget. Get a reduced core scope, request decisions and a teaser-to-preview plan.
  • A smaller launch for the same date, with the core first, a ranked list and a later list of what was cut
  • A teaser, preview and launch plan, with a sign-up page, a handful of insiders, a free sample and the launch message
  • A ruling of yes, later or no on each request, with the full cost of every yes and a short reply for the customer
• Launch scope cutter: Cut your launch scope without moving the date. Paste your plan, date and budget. You get a smaller core launch and a parked list for later.
  • The date and budget locked, with scope as the only thing that moves
  • The heart of the product in one sentence
  • A cut list in rounds, down to the core, ranked by first-customer need
  • A parked list for later, and what the smaller launch still promises
• Launch teaser and preview planner: Plan a product launch teaser from your date. Get a dated plan, sign-up page spec, free sample and launch message so people are waiting on day one.
  • A dated plan from months out to launch day
  • A list of insiders and an early-look offer
  • A promo site spec with a sign-up above the fold
  • A free sample, one teaching piece and the launch message
• Feature request screener: Screen your feature requests and get a yes, later or no on each, with the full cost of every yes and a kind reply for the customer.
  • A repeat count per request, from different people, over time
  • The hidden costs of each request that repeats
  • A yes, later or no with one reason, and the vision conflict named
  • A short reply for each customer that promises no date
• 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.
• Jason Fried: Cut a project to a focused first version through Jason Fried’s recorded approach. Keep the core useful, reduce scope and protect a calmer workweek.
  • Your problem worked on the way Jason Fried would: their questions, their method, their push-back
  • The answer or the work, in Jason Fried'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

• A launch is running late or has grown too big, and the date matters more than the extras.
• You have a long list of feature requests and no clear way to say no without losing goodwill.
• You have a product close to ready but no plan to build an audience before launch day.

Limits to check before starting

• You have no plan yet and only an idea: write down the plan first, or ask a friend to poke holes in it, then come back.
• You want to judge feature requests on a product that is already live: use the Feature request screener on its own.
• You want to test whether anyone wants the product: run a small test with real people first, such as the Minimum experiment planner.

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 three skill files, in the order they run: Launch scope cutter, Launch teaser and preview planner and Feature request screener.
• Give the folder to Claude (in Claude Code, or as files in a Claude Project) and say "Follow HANDOFF.md".
• Give it your plan, date and budget, and paste any feature requests.
• It works step by step and saves each result. Check the cut list before you read the rest, since the later steps use it.
• Tell your team what is cut before anyone builds, and keep the later list somewhere safe.

Read it as data

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