Hire an AI staff exit and announcement planner

Everything it can hand back

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

• An exit plan: who decides, the order of events, the offer and the words to use
• Risk flags on notice, final pay timing, severance and release terms, for a lawyer or HR to check
• A handover, access and exit interview checklist
• The team announcement and answers to likely questions, sent only when you say so

How it does the job well

• Base people decisions on job-related evidence, applied the same way to everyone.
• Write in plain, respectful language the person affected could read.
• Keep personal data to what the task needs, and handle it privately.
• Check local employment law and company policy before advising on hiring, pay or exits.

Mistakes it avoids

• Biased wording in job ads, reviews or interview questions.
• Plans with no owner, timing or way to check progress.
• Treating a template as legal advice.

What a good result looks like

An example, not your task: Money has run short and you have to cut one or more roles.

• Step 1: Exit plan. Who decides, the order of events, the offer, where and when they hear it, and the words to use.
• Step 2: Risk flags. Notice, final pay timing, severance and release points, and reasons that could read as unfair, for a lawyer to check.
• Step 3: Handover. A handover checklist, an access and kit list with dates, and exit interview questions.
• Step 4: Announcement. The team message, who hears first, and honest answers to the questions people will ask.
• 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 Tobi Lütke and Ben Horowitz would. This is a way of reviewing the work. It does not mean they wrote or endorse it.

Capabilities

• Plan the exit. Sets who decides, the order of events, the offer, and the plain words to use, following Horowitz and Chesky.
• Flag the legal risks. Flags notice, final pay timing, severance and release points, and reasons that could read as unfair, for a lawyer to check.
• Build the handover. Builds the handover checklist, the access and kit list with dates, and the exit interview questions.
• Check, then hold the conversation. A pause. Have a lawyer or HR check the plan and the flags. Hold the conversation yourself, in person, with the offer in writing. Only then go on.
• Write the announcement. Writes the team announcement, who hears it first, and honest answers to the questions people will ask. You decide when it goes out.

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 let-someone-go-fairly-and-tell-the-team-well 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/let-someone-go-fairly-and-tell-the-team-well/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 situation: who, why, and whether it is a layoff or a dismissal
• Where they work (country and state), their contract type and start date
• What you can offer: notice, severance, references, help finding work
• Any plan or notes you already have (optional)

Helpful context (optional)

• The person's contract and your handbook
• Any feedback notes or reviews on file
• Your state or country's final pay rule, if you know it

Tools and access

• Any good chat AI: Every step is a plan or a document for you to check.
• A lawyer or HR adviser: The risk flags are a first check, never the final word.
• Any good chat AI: It drafts scripts and messages in plain text from your facts.
• An HR or employment adviser: Rules on notice, pay and consultation differ by country and need a person who knows them.
• Any good chat AI: This is a writing job that any strong chat AI does well.

Functions and deliverables

• Staff exit and announcement planner: Share the situation, records and local requirements. Get an exit-plan draft, risk flags, handover checklist and a later team announcement.
  • An exit plan: who decides, the order of events, the offer and the words to use
  • Risk flags on notice, final pay timing, severance and release terms, for a lawyer or HR to check
  • A handover, access and exit interview checklist
  • The team announcement and answers to likely questions, sent only when you say so
• Layoff plan writer: Plan a layoff with a decision check, a manager script and a company message. Give it your cuts and cash. It writes the plan in your voice.
  • A decision check that says if the cut is needed and final
  • A reason for each cut tied to a capability, not to a person
  • A manager script for one-to-one talks
  • A company message that owns the decision, and a note for those who stay
• Employee termination risk reviewer: Share the employee’s location, reason and known facts. Get risk flags, researched local rules and points that need review before action.
  • High-risk flags checked one by one
  • An escalation recommendation
  • Final pay timing
  • Severance and release points
  Source: Anthropic.
• Offboarding plan builder: Share the role, leave date and local requirements. Draft checklists, exit questions and a handover plan for HR review.
  • A dated offboarding checklist by owner
  • A knowledge handover template
  • Exit interview questions
  • A script for telling the team
  Source: Tuan Duc Tran.
• Staff announcement writer: Say what is changing. Get a clear internal announcement, a rollout plan and answers to likely questions.
  • A plain announcement
  • One version for each channel you use
  • Talking points for managers
  • A FAQ of 5 to 8 questions
  • A rollout order with timing
  Source: Tuan Duc Tran.
• me.md builder: Answer a few questions, or let your AI use what it remembers. Get one private file that tells any AI who you are.
  • One me.md file with up to ten dated sections
  • A list of facts taken from memory, for you to check
  • A short note of what it removed for privacy
  • The two next steps, to save it and set it up
• Tobi Lütke: Review a product or process using Tobi Lütke’s recorded approach. Start with the user, simplify work and check which choices can be undone.
  • Your problem worked on the way Tobi Lütke would: their questions, their method, their push-back
  • The answer or the work, in Tobi Lütke's voice, using their ideas by name
  • Anything that goes beyond their public record, marked
  • One suggested next step
• Ben Horowitz: Prepare a team update or hard management choice using Ben Horowitz’s recorded approach. Name the problem and who owns the next step.
  • Your problem worked on the way Ben Horowitz would: their questions, their method, their push-back
  • The answer or the work, in Ben Horowitz'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

• Money has run short and you have to cut one or more roles.
• Someone has not met a clear standard after real feedback and a fair chance, and it is time.
• You have never let anyone go and do not want to learn by making the mistakes.

Limits to check before starting

• You have no feedback on file for a dismissal: run a fair performance process first, with written feedback and a chance to improve, then come back.
• You have not decided whether to cut a role: review the restructure with your team or an adviser first, then use this once the decision is made.
• You need legal advice on a real claim or contract dispute: talk to an employment lawyer or HR adviser, because the risk flags here are a first check only.

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 situation, the location and what you can offer. It plans the exit and flags the risks.
• Have a lawyer or HR check the plan and the flags. Then hold the conversation yourself, in person.
• Come back for the announcement. Read it, change what needs changing, then send it.

Read it as data

Read the complete role setup as JSON. Connect your AI to the AI Blocks MCP library and read aiblocks://roles/let-someone-go-fairly-and-tell-the-team-well 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.