Hire an AI constructive feedback message planner

Everything it can hand back

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

• One behaviour written so anyone could watch it, with their likely reason and the smallest fix
• A message with true praise, the plain request and a way for them to save face
• The same message with every order turned into a question or request with their gain
• A plan to notice and praise each step in the right direction

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: Someone's work or conduct has slipped and you have put off saying so.

• Step 1: Behaviour and fix notes. One watchable behaviour, why they may do it, their true strengths and the smallest fix.
• Step 2: The message. A short message with true praise, one plain request, what you own and a way for them to save face.
• Step 3: Orders into requests. The message with every order turned into a question or request that shows their gain.
• Step 4: The praise plan. Three stages of progress, specific praise for each, where to say it and what to do if they slip.
• 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 Abraham Lincoln and Dale Carnegie would. This is a way of reviewing the work. It does not mean they wrote or endorse it.

Capabilities

• Gets the behaviour and the fix clear. Decides if it is worth raising, names one behaviour anyone could watch, checks your part, finds a fair reason and lists true strengths.
• Writes the message. Opens with true praise, joins it to the change with "and", points at the mistake gently, owns your part and leaves a way to save face.
• Turns orders into requests. Finds every command and blame line and rewrites each as a question or a request with the person's gain, a good name and a small first step.
• Plans the praise. Splits the change into stages and writes specific, honest praise for each, with the setting and a plan for a slip.

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 give-criticism-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/give-criticism-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

• Who the person is and how you work together
• What keeps going wrong, with one or two real, dated examples
• The result you want instead
• What you honestly value in them (optional)

Tools and access

• Any good chat AI: Sorting events into behaviour, reason and fix is text work any strong chat AI does well.
• A notes app: Keep one note per person for strengths and past talks.
• 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: Rewriting text in a set tone is work any strong chat AI does well.
• Your email or chat app: Read the draft where it will be seen, so the length and tone fit.
• Claude, ChatGPT or Gemini: Writing specific, sincere lines from a short brief is text work. No files, web access or paid tools needed.
• Your calendar: Set the checks as repeating reminders so the praise does not lapse.

Functions and deliverables

• Constructive feedback message planner: Describe the behaviour, desired change and real strengths. Get a feedback draft, clearer requests and a plan to recognise progress.
  • One behaviour written so anyone could watch it, with their likely reason and the smallest fix
  • A message with true praise, the plain request and a way for them to save face
  • The same message with every order turned into a question or request with their gain
  • A plan to notice and praise each step in the right direction
• Feedback notes writer: Share real examples and the change you want. Get clear feedback notes, supported strengths and a small next step.
  • One behaviour, written so anyone could watch it, and the result you want
  • A fair reason the person may act this way, and a question to check it
  • A list of true strengths, with the one closest to the problem marked
  • The smallest fix, with notes to keep, change and leave out
• 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
• Polite request editor: Turn bossy messages into requests people say yes to. Paste your draft and get each order rewritten with their gain and a small first step.
  • The rewritten message, with a question or request in place of each order
  • A list of what changed in each line and why
  • The gain for them that each line uses, and where it came from
  • A check that the ask is still clear
• Small-win praise planner: Make a change stick after a hard talk. Get three stages of progress to look for, honest praise for each and when to say it.
  • Three stages of the change, from first sign to full habit
  • Praise lines for each stage, with a slot for the detail you saw
  • When and where to say them, and how to notice each stage
  • A plan for a slip, and what not to say
  • A date to taper off and review
• 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
• Abraham Lincoln: Work through team conflict, hard choices and plain speeches using Abraham Lincoln’s recorded approach. Start with facts and a shared goal.
  • Your problem worked on the way Abraham Lincoln would: their questions, their method, their push-back
  • The answer or the work, in Abraham Lincoln's voice, using their ideas by name
  • Anything that goes beyond their public record, marked
  • One suggested next step
• Dale Carnegie: Rewrite a tense message or prepare a people conversation using Dale Carnegie’s recorded approach. See the other side, give sincere credit and ask clearly.
  • Your problem worked on the way Dale Carnegie would: their questions, their method, their push-back
  • The answer or the work, in Dale Carnegie'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

• Someone's work or conduct has slipped and you have put off saying so.
• You have asked for the same change more than once and nothing happened.
• You must correct a senior person, a peer or someone who takes things hard.

Limits to check before starting

• You face a serious conduct issue, such as harassment or safety: go to your HR process or a person who handles formal cases, not this message.
• You want to thank or praise someone with no problem to raise: use the Honest thank-you note writer.
• You need to give bad news to a customer or client: use the Bad news 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's a zip with HANDOFF.md plus one skill file for each step.
• Give the folder to Claude (in Claude Code, or as files in a Claude Project) and say "Follow HANDOFF.md". This needs a Claude plan that includes Claude Code or Claude Projects. A free chat tool that cannot open a folder of files cannot run it.
• Describe the person, what keeps going wrong and the result you want. It first checks the matter is worth raising, and stops if it is not. Then it works step by step and saves each result.
• Say or send the message. Then watch for the first small improvement and start the praise 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/give-criticism-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.