This is taking longer than expected.

Try againBrowse the library
AI Blocks

All AI specialists

Hire an AI new hire onboarding reviewer

Plan a new hire’s first 90 days and review real check-in notes. Find blockers and give the manager up to three actions.

What you give

  • The new hire's role, team, start date, manager and buddy
  • The three to five things the role should do well by day 90
  • Your check-in notes each Friday, with what is done, late or blocked

What you get

  • A pre-start list, a first-week plan and goals for days 30, 60 and 90
  • A short set of weekly check-in questions
  • Each week, a call of on track, behind or blocked, with the reason from your notes
  • Up to three actions for you, and any fix on the company's side

An example

Someone is starting soon and you want the first 90 days planned and followed.

You ask: “Plan a new hire’s first 90 days and review real check-in notes. Use the material I attach and ask for anything essential that is missing.”

You get back:

  • plan.md. The pre-start list, day one, week one, and goals for days 30, 60 and 90.
  • checkin-questions.md. Five short questions you ask the new hire each week.
  • This week. Week number, path (on track, behind or blocked) and the share of planned items done.

An example, not your task.

Hire this specialist

It is free and needs no account. Download the pack, give it to your AI and tell it the job. Your AI asks for anything it is missing, then does the work and checks it.

Download the specialist

Related specialists

Skills and workflows for this job: Lead and manage people

Details

Everything it can hand back

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

  • A pre-start list, a first-week plan and goals for days 30, 60 and 90
  • A short set of weekly check-in questions
  • Each week, a call of on track, behind or blocked, with the reason from your notes
  • Up to three actions for you, and any fix on the company's side
  • A draft check-in message that you send yourself

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

  • Treating a late task as a sign of a weak hire in week one or two. Most early delays are missing access or unclear asks.
  • Writing the new hire's own words into any file that may be used in a review.
  • Adding more tasks to a behind week. Cut or move items first.
  • Sending the check-in questions yourself. The manager asks them in person.
  • 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: Someone is starting soon and you want the first 90 days planned and followed.

  • plan.md. The pre-start list, day one, week one, and goals for days 30, 60 and 90.
  • checkin-questions.md. Five short questions you ask the new hire each week.
  • This week. Week number, path (on track, behind or blocked) and the share of planned items done.
  • Why this path. Items done, late and blocked, and the words in your notes that decided it.
  • Do this week. Up to three actions, each with an owner and a day.
  • Fix on our side. Missing access, docs, buddy time or unclear priorities found in your notes.

How the work is checked

  • The path was chosen from the notes and the plan, and the share done is shown with its sums.
  • Company-side causes were listed before any note about the person.
  • No judgment of the person's ability, attitude or fit was written.
  • Anything about safety, discrimination, health or a complaint was passed to a person, not handled here.
  • 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 Andy Grove would. This is a way of reviewing the work. It does not mean they wrote or endorse it.

Capabilities

  • Build the plan once. Makes the pre-start list, day one and week one, then the goals for days 30, 60 and 90. You approve it first.
  • Set the check-in questions. Writes five short questions you ask the new hire each week, such as what is unclear and what is blocking.
  • Read this week. Marks each planned item done, late or blocked from your notes and works out the share done.
  • Choose the path. On track keeps it short. Behind looks first at access, buddy time and unclear priorities. Blocked or worried goes to the top.
  • Update the log. Adds one line per week, so next week it can tell whether the same cause came up again.
  • Hand back three actions. Gives you at most three things to do this week, plus a draft message you send yourself.

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 new-hire-onboarding-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/new-hire-onboarding-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

  • The new hire's role, team, start date, manager and buddy
  • The three to five things the role should do well by day 90
  • Your check-in notes each Friday, with what is done, late or blocked
  • The new hire's answers to the weekly check-in questions

Helpful context (optional)

  • Your standard list of accounts and equipment for the role
  • A description of the team and who the buddy is

Tools and access

  • Claude Code: It can keep the onboarding folder and the log, and run the Friday check on a timer.
  • Google Calendar: Put the Friday check-in on the calendar so the notes are fresh. Booking stays with you.
  • Any good chat AI: This is a writing and reading job. Claude, ChatGPT or Gemini all do it well.
  • Google Forms or your survey tool: You send the survey from there. The AI writes the questions only.

Functions and deliverables

  • New hire onboarding reviewer: Plan a new hire’s first 90 days and review real check-in notes. Find blockers and give the manager up to three actions.
    • A pre-start list, a first-week plan and goals for days 30, 60 and 90
    • A short set of weekly check-in questions
    • Each week, a call of on track, behind or blocked, with the reason from your notes
    • Up to three actions for you, and any fix on the company's side
    • A draft check-in message that you send yourself
  • New hire plan builder: Share a name, role and start date. Get a pre-start checklist, a first week plan, and 30/60/90 day goals.
    • A pre-start checklist
    • An hour-by-hour first day
    • A first week plan
    • 30, 60 and 90 day goals
    • A key contacts table
    Source: Anthropic.
  • 30-60-90 day onboarding planner: Share the role, goals, team and time available. Get a new-hire plan with first-week tasks, milestones and check-ins.
    • A pre-day-1 checklist
    • A day-1 schedule and a first-week reading list
    • Goals for day 30, day 60 and day 90, fitted to the role
    • A buddy guide and a manager check-in plan
    • A retrospective template for day 90
    Source: RampStack.
  • Employee feedback survey planner: Plan staff surveys and focus groups, or review supplied results. Get questions, a reading plan and clear follow-up actions.
    • Survey questions grouped by theme, with an answer scale
    • A focus group or stay interview guide
    • A way to read the results and find the top themes
    • An action plan with owners and dates
    • A guide for managers to discuss team results
    • A launch and follow-up plan
    Source: Tuan Duc Tran.
  • Task list manager: Keep one task list file current. Tell your AI what you add, finish or wait on, and it moves each item to the right section.
    • A TASKS file with four clear sections
    • Items moved and updated as you report
    • A review of open and stuck work
    Source: Anthropic.
  • 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
  • Andy Grove: Set team goals or examine a business threat using Andy Grove’s recorded approach. Find the limiting step, paired measures and the right decision owner.
    • Your problem worked on the way Andy Grove would: their questions, their method, their push-back
    • The answer or the work, in Andy Grove'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 is starting soon and you want the first 90 days planned and followed.
  • You are a manager who wants a short, steady check each week instead of a plan that sits in a folder.
  • You want to catch missing access or unclear asks while they are still easy to fix.

Limits to check before starting

  • You need a one-day orientation or a plan for a short contractor gig: use a simple checklist and a quick call with the person.
  • You want to judge a hire's performance or decide on probation: talk to your own HR adviser, because this agent never judges the person.
  • You have a safety, health or discrimination complaint: go to HR or a qualified person now, not to this agent.

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.

  • Start a chat with the agent. In Claude Code, add it as a skill or save it in .claude/agents, then give it the hire's details.
  • Read the plan and the check-in questions, change what does not fit, and approve it.
  • Each Friday, write a few lines on how the week went and give them to the agent.
  • Read the hand-back and do the actions yourself. Say yes to any single action you want the agent to take.
  • Run it again next Friday. It reads the log and says if the same cause came up again.

Read it as data

Read the complete role setup as JSON. Connect your AI to the AI Blocks MCP library and read aiblocks://roles/new-hire-onboarding-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.