Hire an AI team size, hiring plan and budget review

Everything it can hand back

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

• Hires and exits against plan, team by team, with the sums
• A call on whether the plan holds, and which scenario applies if it does not
• The people budget against spend, with each gap explained
• Open roles with days open, and the yearly cost of each new role request

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

• Rebuilding the forecast every quarter when the plan holds.
• Putting names or individual pay into any file.
• Ranking new role requests. That is the leaders' call.
• Reading a short-term jump in exits as a trend before a second quarter shows it.
• 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 have a hiring plan and want it checked against what happened every quarter.

• The quarter. Headcount, hires made against planned, and exits against forecast, with the sums shown.
• Path taken. Whether the plan holds or a new forecast and scenarios were built, and why.
• Scenario in force. The base, best or worst case now in use, and the switch signs to watch.
• Budget. Spend against budget by team, with each gap explained.
• Open roles. Each open role with days open and its pipeline numbers.
• New role requests. Yearly cost, hire or contract comparison and budget effect for each request, with no ranking.

How the work is checked

• Every gap is worked out from the files, with the sums shown.
• The forecast was rebuilt only when a trigger was hit.
• No people data in the files names or prices an individual.
• No hire was approved, frozen or posted, and no pay was changed.
• 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.

Capabilities

• Build the base. On the first run, it builds a role-by-role plan and a forecast with a range for you to approve.
• Report what happened. Counts headcount, hires, exits and team health for the quarter from your own data.
• Set it against the plan. Works out hires planned against made and exits forecast against actual, by team, and checks the switch signs from last quarter.
• Choose the path. If any gap is over a fifth, a switch sign was hit or goals changed, it rebuilds the forecast and runs scenarios. If not, it says the plan holds.
• Check the budget and pipeline. Sets people spend against budget by team and reports open roles and how long each has been open.
• Price new roles and hand back. Gives each requested role a yearly cost and a hire or contract comparison, with no ranking, then stops for your decisions.

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 quarterly-headcount-plan-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/quarterly-headcount-plan-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 quarter's headcount by team, with hires and exits, as counts
• Your growth goals and people budget, the first time and when they change
• Actual people spend by team (optional, best)
• Hiring pipeline numbers and any new role requests (optional)

Helpful context (optional)

• Your people budget by team and month
• The growth goals for the next year

Tools and access

• Claude Code: It can keep the headcount folder and read last quarter's files each time. It is a paid product that needs a Claude plan or API credits. Any chat AI works if you paste last quarter's files back in.
• Your HR system or a spreadsheet: Export counts by team, hires and exits here, without names or individual pay.
• Google Sheets or Excel: The month-by-month view is a sheet, and finance will want to change the numbers.
• Any chat AI that reads spreadsheets: It can read your headcount sheet and return the budget as a table you can paste.

Functions and deliverables

• Team size, hiring plan and budget review: Compare planned hires and exits with actual counts. Get forecast changes, budget gaps and role requests for leaders to decide.
  • Hires and exits against plan, team by team, with the sums
  • A call on whether the plan holds, and which scenario applies if it does not
  • The people budget against spend, with each gap explained
  • Open roles with days open, and the yearly cost of each new role request
• Hiring headcount planner: Share team counts, business goals and budget. Get a hiring plan that separates approved roles, backfills and requests, with gaps to resolve.
  • A role by role hiring plan
  • A priority order for hires
  • Conservative, base and fast-growth versions
  • A monthly demand and supply report outline
  Source: Tuan Duc Tran.
• Team size and turnover report writer: Share workforce data and a report question. Get team-size or turnover measures, trends, data gaps and actions for review.
  • A short summary of the main findings
  • A metrics table with trends
  • Detail by team, level or location
  • Recommendations, with which ones need a check first
  • A method note that says how each figure was worked out
  Source: Anthropic.
• Headcount and hiring forecast planner: Share past team counts, exits and business goals. Plan hiring needs with clear assumptions, scenarios and a method suited to your data.
  • A forecast of headcount, exits and hires needed, each with a low to high range
  • Hiring demand by team
  • The method used and why it fits your data
  • A back-test showing how far the method would have missed
  • The gap between the finance target and your bottom-up number
  Source: Tuan Duc Tran.
• Headcount scenario planner: Share your team plan, costs and business assumptions. Compare possible hiring paths, cost changes and signs that would trigger a different plan.
  • Base, best and worst case workforce plans
  • Cost for each scenario
  • Trigger signals to switch plans
  • Actions to take under each scenario
  Source: Tuan Duc Tran.
• People cost budget builder: Share headcount, pay and hiring plans. Get a monthly team budget, assumptions and notes on changes from the plan.
  • A budget by team and cost center, with approved and planned roles apart
  • A month-by-month spend view
  • Attrition savings and shared cost shown as their own lines
  • Variance notes against actuals, with the cause in words
  • A half-page note for finance
  Source: Tuan Duc Tran.
• Hiring progress reporter: Turn your hiring pipeline numbers into a clear update for your hiring manager or leaders. Pick a weekly update, market report, talent map or look back.
  • A readable pipeline update
  • A market or talent map report
  • A simple chart page if you ask
  • Specific recommendations
  Source: Carlo Pezzuto.
• Hire or contract cost checker: Share a role, pay range and work needs. Compare hiring and contractor costs, assumptions and the evidence needed for a business case.
  • A loaded yearly cost table, with each line marked given or assumed
  • A hire versus contractor comparison over the same period
  • A payback estimate, or the output needed to break even
  • A case for finance in under 300 words
  • A list of figures finance should confirm
  Source: Tuan Duc Tran.
• 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

Tasks you can use it for

• You have a hiring plan and want it checked against what happened every quarter.
• You want to know when the plan needs a rebuild and when it only needs a note.
• You want a short update for leaders and the cost of each new role request.

Limits to check before starting

• You have fewer than about 15 people: work out each hire on its own with the Hire or contract cost checker.
• You have no stable goals for the year: write them down first, or the forecast only repeats the past.
• You cannot share people data with an AI: give counts only, or do the check by hand in a spreadsheet.

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 your goals and last quarter's numbers.
• Give counts and roles only. Leave out names and individual pay.
• The first time it builds a plan and a forecast for you to approve. After that it compares each quarter with them.
• Read the update with your leaders. The decisions on hires and budget are yours.
• It does not start by itself. Run it each quarter, or connect a scheduler if your AI app has one.
• For a company of about 15 to 30 people, it judges change by the number of people, not the 20% rule, because one hire moves the share a lot. Under 15 people, use the Headcount business case builder for each hire instead.

Read it as data

Read the complete role setup as JSON. Connect your AI to the AI Blocks MCP library and read aiblocks://roles/quarterly-headcount-plan-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.