Hire an AI evidence-based feedback conversation planner

Everything it can hand back

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

• A conversation plan: where you stand, what to praise, what to say and how to say it
• An opening you can say aloud, built on facts, with one clear request
• Listening questions, and what to do if they push back
• A plain-words edit of the opening, with each change explained
• A follow-up date and what to check
• A list of what was missing and one next step

How it does the job well

• Stop and say so if the facts describe harassment, a threat, a safety issue or a legal matter. Say the person should follow their HR or safeguarding process and take advice before any talk. Do not plan the talk.
• Do not guess the other person's motives. Write them as questions to ask.
• Pin down the exact question, scope and the standard of evidence needed before searching.
• Prefer primary sources, and say how strong each source is.
• Separate what is established, debated and unknown, with confidence levels.
• Cite specifically: author, work, date or page where possible.

Mistakes it avoids

• Presenting one source or a popular claim as settled.
• Inventing citations, quotes or page numbers.
• Over-generalising across places, periods or groups.

What a good result looks like

An example, not your task: A teammate keeps missing deadlines and you have put the talk off.

• Conversation plan. Where you stand, what to praise, what to say and how to say it.
• Opening. Lines to say aloud, built on facts, with one clear request.
• Listening questions. Questions that invite the other person to speak, and what to do if they push back.
• Edited opening. A plain-words version of the opening, with each change and its reason.
• Hand-back summary. Files saved, facts missing, checks not done and one next step.

How the work is checked

• The plan is about one behavior, and every fact comes from what the person gave.
• No line guesses at a motive or calls the person a name.
• The opening has one clear request and a way for the other person to answer.
• The follow-up has a date.
• 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 Charles Darwin and Richard Feynman would. This is a way of reviewing the work. It does not mean they wrote or endorse it.

Capabilities

• Feedback conversation planner. Names the one behavior and its effect, places the talk and sets out the praise, the statement and the questions. It hands the facts and the request to the opening step.
• Hard feedback message writer. Drafts the opening from the facts, with praise joined to the change, one plain statement and a way for the other person to save face. It hands the draft to the editor.
• Plain English editor. Edits the opening and the questions into plain words and explains each change. It keeps what the facts support and leaves room to disagree.

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 plan-a-difficult-feedback-conversation 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/plan-a-difficult-feedback-conversation/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

• One behavior you saw, as what happened, not what you think of the person
• What it caused, for you, for others or for the work
• The facts you can point to, such as dates, messages or examples
• How you know the person, and what change you want
• What you cannot promise or will not discuss
• What the person has said about it before (optional)
• Notes or an earlier draft of what you plan to say (optional)

Helpful context (optional)

• A quote or message that shows the behavior, with the date.
• What you already tried to say before.

Tools and access

• Claude, ChatGPT or Gemini: Any of them can plan the talk from what you type. A person you trust can play the other side so you can practise.
• Any good chat AI: Placing the situation and writing the plan is text work any strong chat AI does well.
• A calendar: Book the talk and the follow-up date straight away.
• Any good chat AI: Rewriting a message in a set tone is text work any strong chat AI does well.
• Your email or chat app: Read the draft in the same place it will be seen, so the length and tone fit.
• Any good chat AI: Editing a draft with a fixed list of moves is text work any strong chat AI does well with this skill.
• A read-aloud tool: Hearing the result spoken shows where a line does not sound like you.

Functions and deliverables

• Evidence-based feedback conversation planner: Share observed behaviour, effects and the desired change. Get a conversation plan, direct opening lines and listening prompts.
  • A conversation plan: where you stand, what to praise, what to say and how to say it
  • An opening you can say aloud, built on facts, with one clear request
  • Listening questions, and what to do if they push back
  • A plain-words edit of the opening, with each change explained
  • A follow-up date and what to check
  • A list of what was missing and one next step
• Feedback conversation planner: Plan a feedback conversation that gets heard. Describe the person and the problem. You get what to praise, what to say and how to say it.
  • Which box on the chart you are in now, and what to change
  • One piece of specific praise to open with
  • The behaviour and effect, in words to say
  • Questions to ask and a follow-up date
• Hard feedback message writer: Share what happened, who needs feedback and the change you want. Get a clear, respectful draft focused on one behaviour.
  • A draft message you can send or say
  • The one behaviour it asks to change, in plain words
  • A list of the true praise it used and where that came from
  • A note on how you could save face for them
• Plain English editor: Paste a draft and get it back in plain English, with every cut explained and a read-aloud check. Edit stiff emails, reports and pages.
  • The edited text in plain words
  • A list of every cut or swap, with its reason
  • The point of the piece in one sentence
  • Questions where a fact was missing
• Research paper and code note writer: Share a paper, repo or messy notes. Get claims, methods and evidence sorted into a clear research folder.
  • A research folder with claims, methods and results
  • Every claim linked to its supporting table or log
  • Results tables copied with exact numbers
  • A record of dead ends and decisions
  • A short report on what was filled in and what was missing
  Source: Orchestra Research.
• Charles Darwin: Build a case using Charles Darwin’s recorded approach. Keep facts that challenge your idea, face the hardest objections and show where the evidence stops.
  • Your problem worked on the way Charles Darwin would: their questions, their method, their push-back
  • The answer or the work, in Charles Darwin's voice, using their ideas by name
  • Anything that goes beyond their public record, marked
  • One suggested next step
• Richard Feynman: Explain a hard idea or check a claim using Richard Feynman’s recorded approach. Use plain examples, seek contrary evidence and test what you can.
  • Your problem worked on the way Richard Feynman would: their questions, their method, their push-back
  • The answer or the work, in Richard Feynman'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 teammate keeps missing deadlines and you have put the talk off.
• A student, volunteer or colleague did something that cost others and you need to raise it.
• You said it once, softly, and nothing changed.
• You are about to write a long message and suspect a calm talk would work better.

Limits to check before starting

• The issue is harassment, safety or a legal case. Follow your HR process and take advice first.
• You are the go-between for two students in conflict. Use the Restorative conversation planner.
• You want feedback on a piece of writing. Use the Long-form draft reviewer.
• You only need the message written, with no talk planned. Use the Hard feedback message 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".
• Paste what happened, what it caused, your facts and the change you want. Leave out your guesses about why they did it.
• Read the opening aloud. If it does not sound like you, change it before the talk.
• Hold the talk in person or on a call, then use the follow-up date from the plan.

Read it as data

Read the complete role setup as JSON. Connect your AI to the AI Blocks MCP library and read aiblocks://roles/plan-a-difficult-feedback-conversation 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.