Hire an AI one-on-one agenda and feedback planner

Everything it can hand back

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

• A one-page agenda per person, their items first
• One specific win per person and the exact praise
• Open items carried forward, with stuck ones marked
• A planned hard conversation only where a problem repeated
• Patterns stuck across the team, which may be yours to fix
• A one-page status update for your manager, when asked

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

• Opening with the hard point.
• Praise so general it could be said to anyone.
• Raising a problem the manager has not seen themselves.
• Asking the go-to question again before acting on the last answer.
• Biased wording in job ads, reviews or interview questions.
• Plans with no owner, timing or way to check progress.

What a good result looks like

An example, not your task: You manage three or more people and your one-on-ones have become status meetings.

• This week in one line. How many one-on-ones, stuck items and hard points you have this week.
• Per-person agenda. One page per person: their items first, open items, the win, any hard point and the go-to question if due.
• Win and exact praise. One specific win from your notes, the words to say and when to say them.
• Hard point plan. For a problem seen two weeks running: the behaviour, the likely reason and how to raise it.
• Team patterns. Anything stuck for more than one person, which may be yours to fix.
• Your update. A one-page status update for your manager, only if you ask, with private notes left out.

How the work is checked

• Every agenda starts with the person's items, not the manager's.
• Every win is specific and from the notes. None was invented.
• No hard point was raised on one week of evidence.
• No person's notes appear in another person's agenda or in the manager's update.
• 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 Kim Scott and Abraham Lincoln would. This is a way of reviewing the work. It does not mean they wrote or endorse it.

Capabilities

• Set up each person once. Sets a meeting rhythm that tightens when someone is new, and writes your go-to question for asking them what to change.
• Read last week. Carries every open item forward, marks ones stuck three weeks, and checks whether you acted on their last answer.
• Find the win. Picks one specific win from the notes and writes the exact praise and when to give it.
• Spot the repeat. When the same problem appears in two weeks of notes, names one watchable behaviour and its likely reason.
• Plan the hard conversation. Only where a repeat exists, plans what to praise, what to say and how, humble and about what happened.
• Build each agenda. Their items first, then open items, the win, the hard point, and the go-to question if due.
• Write your update on request. A one-page status update for your manager, with people's private notes left out.
• Log and hand back. Updates each person's file, then stops.

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 weekly-one-on-one-prep-keeper 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/weekly-one-on-one-prep-keeper/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

• Last week's notes from each one-on-one and anything you noticed, per person (rough one-liners are fine)
• Each person's name, job, time in the role and current work
• Their objectives or key results this quarter (advised)
• A yes if you want a status update for your own manager (optional)
• The person files from earlier weeks, once they exist (optional on week one)

Helpful context (optional)

• What each person said the last time you asked what you should change
• Each person's start date in the role, so the rhythm is right

Tools and access

• Claude Code: It can keep one private file per person and run every Monday before the first meeting.
• Any good chat AI: Paste the agent and your notes for the week. Keep the person files in a private note.
• Any good chat AI: Structuring decisions and writing plans is text work any strong chat AI does well with this skill.
• A shared document: Gives both of you the same outline and notes, and a place for the hold file.
• Claude, ChatGPT or Gemini: Writing a few lines in your voice is text work. No files, web access or paid tools needed.
• Your calendar: Put the ask on the last five minutes of each one-to-one so it happens every time.
• 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.
• 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: 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: A one-message prompt works in any strong chat AI, with nothing to install.

Functions and deliverables

• One-on-one agenda and feedback planner: Prepare a short agenda from real notes. Carry open items, find specific wins and plan supported feedback privately.
  • A one-page agenda per person, their items first
  • One specific win per person and the exact praise
  • Open items carried forward, with stuck ones marked
  • A planned hard conversation only where a problem repeated
  • Patterns stuck across the team, which may be yours to fix
  • A one-page status update for your manager, when asked
• One-on-one meeting planner: Plan a one-on-one meeting with someone who reports to you. Get how often to meet, an outline they write, meeting rules and follow-up.
  • How often to meet, and how long
  • A meeting outline they write, with the parts you require
  • Rules for the meeting: questions, notes, the hold file
  • A follow-up routine for actions
• Feedback request script writer: Ask your team for honest feedback. You get a go-to question in your voice, a plan for the silence and lines for what you hear.
  • A go-to question in your voice, in two versions with one picked
  • The best moment to ask, so it becomes a habit
  • A plan for the silence after you ask, about six seconds
  • A second question tied to your recent project
  • Lines to repeat back what you heard, reward the honesty and handle a point you disagree with
• 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
• 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
• 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
• Weekly status update writer: Write a weekly status update from your notes. Get a one-page report with an overall call, risks and the decisions you need, in under 250 words.
  • An overall status with a reason
  • Done, in progress, risks and decisions needed
  • Next period's top three
• 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
• 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
• 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

Tasks you can use it for

• You manage three or more people and your one-on-ones have become status meetings.
• You keep forgetting to praise the thing that went well last week.
• A problem has come up twice and you are not sure how to raise it.
• A new hire starts and you want a meeting rhythm that fits their first weeks.

Limits to check before starting

• You manage one or two people. A shared note and a good question may be all you need.
• You are writing the end-of-quarter review. Use the Employee performance review writer, which reads these files.
• A problem is serious now, such as a safety issue or a policy breach. Raise it yourself at once. Do not wait for two weeks of notes.
• You want notes from a meeting turned into minutes or action items. Use the Rough-note meeting minutes 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.

• Open the agent in Claude, ChatGPT or Gemini, or paste it into a new chat. In Claude Code, add it as a skill or save it in .claude/agents so it can keep one file per person.
• Paste last week's notes for each person, or point it to your private folder of notes. Leave out anything you would not want written down.
• On the first run, give each person's job and how new they are. It sets up the rhythm and the go-to question, and starts the repeat check next week.
• Read each agenda before the meeting. Check that every win and every hard point comes from your notes. Change what does not fit.
• Hold the meeting yourself. Afterward, add your notes and run it again next Monday. At quarter end, hand the files to the Quarterly performance review keeper.

Read it as data

Read the complete role setup as JSON. Connect your AI to the AI Blocks MCP library and read aiblocks://roles/weekly-one-on-one-prep-keeper 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.