Hire an AI team capacity and delivery-date planner

Everything it can hand back

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

• A capacity view of available hours against committed work for the window
• Where people are overloaded and where there is room
• Two or three delivery date options, each with what it assumes and what could go wrong
• A draft reply to the requester for you to review before anything is promised
• The facts still missing, so you know what to confirm

How it does the job well

• Start from the user problem and the evidence for it, then the solution.
• Write decisions down with the reason and the options you rejected.
• Keep scope small enough to ship and learn. Name what is out of scope.
• Define how success will be measured before building.

Mistakes it avoids

• Treating opinions or one loud request as proven demand.
• Specs that skip edge cases, error states or dependencies.
• Roadmaps with dates but no owners or confidence levels.

What a good result looks like

An example, not your task: A customer or boss asks for a delivery date and your team is already busy.

• Capacity view. Available hours against committed work per person for the window, with who is overloaded and who has room.
• Risk list. Shared people, waiting dates and the jobs most likely to slip if you take the new work.
• Delivery options. Two or three dates, each with what it assumes, what could go wrong and what gives way.
• Draft commitment. A short reply to the requester with the date range and its conditions, for you to review.
• Hand-back summary. Files saved, facts that could not be checked and the single next step.

How the work is checked

• Existing commitments are still counted after the new work is added.
• Effort is shown as a range and every waiting date is named.
• Every figure and date traces to a source or is labelled as an assumption.
• The draft reply promises nothing the options do not support and is marked as not sent.
• 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

• Team capacity planner. Works out available hours in the window against committed work, per person. It hands the capacity table and the overloaded list to the next step.
• Project risk and portfolio manager. Sets the new request against your other work and flags shared people, waiting dates and the jobs most likely to slip. It hands the risks to the writer.
• Stakeholder update writer. Turns the capacity and risks into delivery date options with trade-offs, then drafts a short reply to the requester. It does not send it.

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 check-capacity-before-promising-a-delivery-date 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/check-capacity-before-promising-a-delivery-date/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

• Your committed work: each job, who is on it and its due date
• A low, likely and high effort estimate for each job, in hours or days
• Who is available in the window and for how many hours, after leave and meetings
• What each job waits on, such as a supplier, a customer reply or a person
• The new request: what it is, the date asked for and any date that cannot move
• Your priorities or rules, such as which customers come first (optional)

Helpful context (optional)

• Leave and holiday dates for everyone in the window.
• What happened the last time a similar job ran long.

Tools and access

• Claude, ChatGPT or Gemini with file support: They can read a spreadsheet export of your jobs and show each sum. A project tool is not required.
• Any good chat AI: It needs your numbers pasted in. A tracker or calendar connection saves typing.
• Any good chat AI: It only needs your notes pasted in. A tracker connection is a bonus, not a need.

Functions and deliverables

• Team capacity and delivery-date planner: Check team hours and work already promised. Review risks and draft delivery options before you agree to a new date.
  • A capacity view of available hours against committed work for the window
  • Where people are overloaded and where there is room
  • Two or three delivery date options, each with what it assumes and what could go wrong
  • A draft reply to the requester for you to review before anything is promised
  • The facts still missing, so you know what to confirm
• Team capacity planner: Give it your team and projects. Get workload against people, who is overloaded, and whether you can take on more.
  • A table of hours available, hours used and percent full for each person
  • A list of who is over or under their target
  • Which coming projects fit and which leave a gap
  • Three to five options with the hours each one frees up
  • One recommendation, and what would change it
  • A list of assumptions and missing facts
  Source: Anthropic.
• Project risk portfolio planner: Share project risks, scores, owners and resource needs. It compares exposure and workload, then drafts priorities and status for review.
  • Risk register with expected cost
  • Priority ranking of projects
  • Resource load check
  • Health scores and status colours
  • Executive summary
  Source: Alireza Rezvani.
• Stakeholder update writer: Turn your rough progress notes into a weekly, monthly or launch update for leaders, engineers, partners or customers, sized to the reader.
  • A draft update sized to your reader, ready to paste
  • A status colour with a one-line reason
  • Each risk with a plan or an owner
  • Each decision with options and a recommendation
  • A list of facts you still need to add
  • A version for a second reader (optional)
  Source: Anthropic.
• Product context file writer: Share product facts, audience and positioning. Get a reviewed context file that other marketing skills can reference.
  • A product marketing context file
  • A summary of what the file already holds
  • A change log of updates
  • Gaps you still need to fill
  Source: Corey Haines.

Tasks you can use it for

• A customer or boss asks for a delivery date and your team is already busy.
• A new request arrives and you must decide what slips if you take it.
• Two people promised the same hours to different jobs.
• You want a date range you can defend, not a best guess.

Limits to check before starting

• The date is already fixed in a contract or signed order. This does not change commitments you have made.
• You have no list of current work or who is available. Gather that first, or use the Team capacity planner on its own.
• You want to know what your team's hours earn after costs. Use the Service capacity and cost reviewer workflow.
• You are checking a product mix against machine or plant limits. Use the Product mix capacity checker.

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 is a zip with HANDOFF.md and every skill file this workflow uses.
• Give the folder to Claude, ChatGPT or Gemini and say "Follow HANDOFF.md".
• Paste your committed work, effort ranges, availability and the new request. A spreadsheet export works.
• Check the capacity view first. If a person's hours look wrong, fix them before the options are built.
• Read the date options and the draft reply, edit the reply and send it yourself.

Read it as data

Read the complete role setup as JSON. Connect your AI to the AI Blocks MCP library and read aiblocks://roles/check-capacity-before-promising-a-delivery-date 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.