Hire an AI peer feedback session and revision planner

Everything it can hand back

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

• A session plan with who sits in the room, who stays quiet first and the rule for notes
• Raw comments rewritten as specific problem notes, with fixes kept as examples only
• Each problem traced to its likely cause, with notes that may name the wrong spot
• Three to five headlines, what to blow up and keep, a choice sheet for you and the date of the next look

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: Your work is stuck or still rough and you want honest notes from people you trust.

• Step 1: The review session. Who sits in the room, who speaks last, a timed plan, the note rule and a follow-up date.
• Step 2: Good notes. Each raw comment rewritten as a problem note with its place, what the reader lost and who raised it.
• Step 3: Causes. Each problem traced to its likely cause, with notes that may point at the wrong spot flagged.
• Step 4: The fix plan. Three to five headlines, what to blow up, go back on and keep, and your choice sheet.
• Hand-back summary. Each step's file, any step not run and every gap marked MISSING 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 Ed Catmull and Kim Scott would. This is a way of reviewing the work. It does not mean they wrote or endorse it.

Capabilities

• Plans a session peers can be honest in. Picks reviewers with no power over you, keeps the most senior voices quiet at the start and sets the rule that notes name problems and not fixes.
• Sharpens the comments. Sorts each comment into problem, fix, order, feeling or comment on you, and rewrites it as a specific problem with its place.
• Traces the cause. Reads each spot on its own, looks earlier in the work and flags notes that may name the wrong symptom.
• Headlines it. Boils the notes down to a few headlines and asks what to blow up, what to go back on and what you still love.
• Leaves the choice to you. Gives you a sheet to mark Act, Test first or Decline, and sets the next review and a stuck test.

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 rough-work-feedback 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/rough-work-feedback/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 work, or a description of it, and what is stuck
• The people who could review it, with their roles and whether they have power over you
• How long the session is and where it is held
• After the session, every comment as it was said

Tools and access

• Any good chat AI: Turning a project and a list of people into a plan is text work any strong chat AI does well.
• A shared document: Reviewers write problem notes in one place the owner can read afterwards.
• Any good chat AI: Sorting and rewriting comments is text work any strong chat AI does well with this skill.
• A shared document: Reviewers can add their answers to the questions beside each note.
• Any good chat AI: Tracing causes from notes is text reasoning any strong chat AI does well with this skill.
• A copy of the work with line numbers: Lets each cause point at a specific part.
• Any good chat AI: Condensing and ranking a list is text work any strong chat AI does well with this skill.
• A calendar: Put the next review date in it the same day.

Functions and deliverables

• Peer feedback session and revision planner: Share rough work and reviewer context. Get a session plan, sharper problem notes and a revision plan after real feedback.
  • A session plan with who sits in the room, who stays quiet first and the rule for notes
  • Raw comments rewritten as specific problem notes, with fixes kept as examples only
  • Each problem traced to its likely cause, with notes that may name the wrong spot
  • Three to five headlines, what to blow up and keep, a choice sheet for you and the date of the next look
• Peer feedback session planner: Plan a peer feedback session for a stuck project. Get the reviewers, timings and note rules that help people say what is not working.
  • A list of reviewers chosen, with anyone left out and the reason for each
  • The session plan, with rules, timings and who speaks when
  • A form for notes that records problems, not fixes
  • A follow-up date and the question to ask then
• Draft feedback editor: Turn vague or bossy feedback into clear notes on the problem. Paste your raw comments and get each one rewritten with its place and any fix as an example.
  • Each comment rewritten as a problem note with its place and what the reader lost
  • Fixes kept on their own line, marked as examples only
  • Repeats merged and counted
  • A list of questions to send back to reviewers, and a list of comments that were about you, not the work
• Problem root cause tracer: Find the root cause behind problem notes on your work. Paste the notes. You get likely causes ranked, plus notes that may point at the wrong spot.
  • Each problem with whether the spot holds up on its own
  • Likely causes upstream, grouped, with a hold-test answer for each
  • A list of notes that may name the wrong symptom
  • A first quick check for each top cause, and what result would prove it
• Revision headline planner: Turn a long list of review notes into three to five headlines, a choice sheet and a next-version plan with a review date.
  • Three to five headlines, each with the notes under it
  • Answers to what to blow up, what to go back on and what you love
  • A choice sheet for you to fill in, marking Act, Test first or Decline
  • A first move for this week, the next review date and a stuck test
• 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
• Ed Catmull: Plan feedback or protect rough creative work using Ed Catmull’s recorded approach. Name the problem, keep the creator’s choice and find hidden issues.
  • Your problem worked on the way Ed Catmull would: their questions, their method, their push-back
  • The answer or the work, in Ed Catmull's voice, using their ideas by name
  • Anything that goes beyond their public record, marked
  • One suggested next step
• Kim Scott: Prepare feedback using Kim Scott’s recorded approach. Ask for criticism, describe the work clearly and follow up with care.
  • Your problem worked on the way Kim Scott would: their questions, their method, their push-back
  • The answer or the work, in Kim Scott'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

• Your work is stuck or still rough and you want honest notes from people you trust.
• The feedback you get is either polite or bossy.
• You have a pile of comments and do not know where to start.

Limits to check before starting

• Your work is finished and needs sign-off or an expert check: ask a named expert or approver to review it instead.
• You want one person to edit your wording line by line: ask a single trusted reader for an editing pass instead.
• You have no reviewers and no comments yet: ask two or three peers to look at the work first, then come back.

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 pack. It holds HANDOFF.md and four skill files, in the order they run: Peer feedback session planner, Good note sharpener, Problem root cause tracer, then Revision headline planner.
• Give the folder to Claude, in Claude Code or as files in a Claude Project, and say "Follow HANDOFF.md".
• Step 1: paste your work and the people who could review it. Then hold the review session and write down every comment.
• Step 2: paste all the comments, with who said each one. Steps 3 and 4 then run from the notes.
• Read the headlines, then fill in the choice sheet yourself. The workflow never decides for you.

Read it as data

Read the complete role setup as JSON. Connect your AI to the AI Blocks MCP library and read aiblocks://roles/rough-work-feedback 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.