Hire an AI partner launch announcement and approval planner

Everything it can hand back

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

• A shared message brief: the agreed facts, the claims each side may make and words to avoid
• An audience and approver map: who you tell and who checks each message
• A core announcement and one draft for each audience, in the right voice
• An approval tracker: each draft, its audience, approver, status and date
• A hand-back summary with one next step

How it does the job well

• Use only facts both sides agreed. Never invent a date, price, quote, number, benefit or customer name.
• A claim about the partner is only used if the partner's own approved messaging contains it.
• Use the partner's name and logo only as their rules allow.
• Every draft is marked "unpublished" until the named approvers approve it. A draft is not a published announcement.
• Keep private contract terms out of every public draft.
• Write for one named audience and one action. Each asset has a single job.
• Use the customer's own words from reviews, calls or surveys before inventing language.

Mistakes it avoids

• Generic copy that could fit any brand.
• Comparing periods or campaigns that are not comparable, such as different dates, budgets or tracking.
• Calling a test winner before there is enough data.

What a good result looks like

An example, not your task: You and a partner have signed a deal and a launch date is set, and you need the announcement

• Shared message brief. The agreed facts, the claims each side may make, words to avoid and open questions.
• Audience and approver map. Each audience, what they need to know and who must approve on each side.
• Core announcement. The main message, using only the agreed facts.
• Audience versions. One draft per audience, edited to the right brand's voice, with joint claims unchanged.
• Approval tracker. Each draft with its audience, approver, status and date, all unpublished until approved.
• Hand-back summary. Files saved, MISSING facts, checks not done and one next step.

How the work is checked

• Every fact in every draft is in the shared brief.
• The date, names, offer and joint claims match across all drafts.
• No claim about the partner goes beyond the partner's approved messaging.
• Every draft is marked unpublished, with an approver named or MISSING: approver.
• 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 Ann Handley and Claude Hopkins would. This is a way of reviewing the work. It does not mean they wrote or endorse it.

Capabilities

• Stakeholder map builder. Maps the audiences you will tell and the people who must check the announcement on each side. It hands on the audiences, approvers and agreed facts.
• Stakeholder update writer. Writes a one-page shared brief, then a core announcement and a version for each audience, from the agreed facts. It hands on the brief and every draft.
• Brand voice editor. Checks each version against the right brand's voice and keeps joint claims the same in every draft. It hands back drafts ready for approval.

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 prepare-a-partner-launch-announcement-pack 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/prepare-a-partner-launch-announcement-pack/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 agreed partnership facts: what you are launching, the date, and what each side does
• Each side's approved messaging, and the rules for using each other's name and logo
• A few examples of each brand's voice, such as past posts or emails
• The audiences you will tell, such as your customers, their customers, staff or press
• Where you may post or send it, and who approves on each side (optional)

Helpful context (optional)

• Your brand brain or voice notes, and your partner's if they share them.
• A named contact at the partner for questions on the facts.

Tools and access

• Claude, ChatGPT or Gemini with file support: They read the agreed facts and voice examples and keep each step as a file. They do not send, post or contact your partner. You do that.
• Any good chat AI: It only needs your notes pasted in. A tracker connection is a bonus, not a need.
• Any good chat AI: Claude, ChatGPT and Gemini all do this well when the voice notes and customer quotes are pasted in full.

Functions and deliverables

• Partner launch announcement and approval planner: Share agreed partnership facts and both brands' guidance. Get a shared message brief, announcement drafts and approval tracker.
  • A shared message brief: the agreed facts, the claims each side may make and words to avoid
  • An audience and approver map: who you tell and who checks each message
  • A core announcement and one draft for each audience, in the right voice
  • An approval tracker: each draft, its audience, approver, status and date
  • A hand-back summary with one next step
• Stakeholder map builder: List the people affected by your project. Get a power and interest grid with how to talk to each group.
  • A power and interest grid
  • A strategy for each group
  • Update frequency and channel for each
  • Key messages
  • Risks of ignoring each group
  Source: Pawel Huryn.
• Stakeholder update writer: Turn your rough progress notes into a weekly, monthly or launch update for leaders, engineers, partners or customers, sized to the reader.
  • A draft update sized to your reader, ready to paste
  • A status colour with a one-line reason
  • Each risk with a plan or an owner
  • Each decision with options and a recommendation
  • A list of facts you still need to add
  • A version for a second reader (optional)
  Source: Anthropic.
• Brand voice editor: Paste your ad, voice rules and customer quotes. Get small wording fixes that keep claims intact, plus a line-based voice score.
  • A verdict, on voice or needs fixes, with a one-sentence summary
  • Each off-voice phrase quoted exactly, with the rule or customer quote it breaks
  • The full corrected line for each fix, with numbers and claims unchanged
  • A voice score out of 100 (the share of lines on voice), now and after the fixes
• Brand profile builder: Share your website. Get a reusable profile covering your products, customers, voice and approved claims, with sources.
  • A folder of eight plain files, from a start file for your AI to a claims list and a change log
  • A tag on every fact, and every claim marked approved, pending or banned
  • A two-sentence diagnosis of your biggest gap, and a list of what's missing and who can answer it
  • A short slice for your next step, if you name one
• Ann Handley: Write or revise an email, page or newsletter using Ann Handley’s public approach. Start with the reader’s concern and cut generic lines.
  • Your problem worked on the way Ann Handley would: their questions, their method, their push-back
  • The answer or the work, in Ann Handley's voice, using their ideas by name
  • Anything that goes beyond their public record, marked
  • One suggested next step
• Claude Hopkins: Write specific ads or plan a small buyer test using Claude Hopkins’s recorded approach. Replace vague praise with facts and track cost per customer.
  • Your problem worked on the way Claude Hopkins would: their questions, their method, their push-back
  • The answer or the work, in Claude Hopkins'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 and a partner have signed a deal and a launch date is set, and you need the announcement
• You must tell customers, the partner's customers and your own staff, each in a different way
• Your partner's legal or brand team must approve the wording before anything goes out
• You want one shared set of facts so emails, posts and press notes never disagree

Limits to check before starting

• The partner has not signed off on the deal or the date. Settle the terms first with Partner deal profit planner.
• You want a media list and pitch emails for the press. Use the Press outreach planner.
• You are telling only your own staff about a change. Use the Staff announcement writer.
• You want a progress update for a team or leaders. Use the Stakeholder update writer.

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 is a zip with HANDOFF.md and every skill file this workflow uses.
• Give the folder to Claude, ChatGPT or Gemini and say "Follow HANDOFF.md".
• Share the agreed facts, each side's approved messaging and voice examples, and the audiences. Use only facts both sides agreed.
• Read the shared brief first. Send it to your partner and fix any fact either side disputes.
• Send each draft to its approvers. Record their answers in the tracker. Publish nothing until each draft is approved.

Read it as data

Read the complete role setup as JSON. Connect your AI to the AI Blocks MCP library and read aiblocks://roles/prepare-a-partner-launch-announcement-pack 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.