Hire an AI capstone team agreement and handover reviewer

Everything it can hand back

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

• A list of what changed since the last review, with the source and date of each change
• An updated team working agreement covering file versions, reviews, blockers and handover
• A task register with an ID, owner, due date and status for each accepted commitment
• A question list for tasks with no confirmed owner or date
• A handover note, only if someone becomes unavailable, built from the real state of their work
• A MISSING list, CHECKS MISSED and a short record for the next review

How it does the job well

• Turn every request into owned actions: who, what and by when.
• Work from the real calendar, notes and lists. Never invent meetings, people or dates.
• Put the most important decision or deadline first, then the details.
• Prepare drafts and proposals. Sending, booking and changing records waits for approval.

Mistakes it avoids

• Losing commitments buried in long notes.
• Mixing confirmed facts with guesses about other people's plans.
• Adding process when a short checklist would do.

What a good result looks like

An example, not your task: A team milestone is due and you want the agreement and task list checked against what people really accepted.

• Changed since last review. Each change to the assignment rules or to a commitment, with its source and date.
• Team working agreement. How the team versions files, reviews each other's work, resolves blockers and hands over work.
• Task register. One row per accepted commitment with an ID, task, owner, due date, timezone, status and source. Suggested owners are marked as suggestions.
• Questions to confirm. Tasks with no confirmed owner or date, and who has to answer each one.
• Handover note. Only when a member is unavailable. Urgent items, what is due, live work and where files live. It names no replacement.
• Record for next review. The assignment version, accepted commitments, owners, deadlines and handover gaps, to paste into the next run.

How the work is checked

• The register has one row per accepted commitment, each with an ID, owner, due date, status and source.
• Agreed and suggested owners are shown differently.
• No replacement is named and no agreement by others is assumed in a handover.
• Every fact, date and figure traces to a source or is labelled an assumption.
• 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

• Compare with the last review. Reads the saved record if it belongs to this team and assignment, or sets a first baseline. Lists what changed in the assignment rules and in the team's commitments. If nothing changed and no milestone is due, it says so and stops.
• Update the agreement and the task register. Runs the Capstone team agreement planner. It writes how the team versions files, reviews work, clears blockers and hands over. It then lists each accepted commitment with an owner and due date.
• Separate agreed from suggested. A task someone suggested for another person stays a suggestion until that person confirms. A task with no date or owner goes to the question list.
• Prepare a handover only when needed. If a member becomes unavailable, it runs the Handover note writer on the real state of their work. It names open tasks, files and decisions waiting. It does not pick a replacement.
• Save and hand back. Saves the files and a proposed new record, and keeps the old one. Lists every MISSING line and every check that did not run.

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 capstone-commitment-review-assistant 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/capstone-commitment-review-assistant/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 last review and its record (optional on a first run)
• The assignment rubric or brief, with its version and date
• Each member's real availability, such as weekly hours and dates away
• The deliverables the team agreed, and the decisions already made (from notes, chat or minutes)
• The team's rules for working together, such as file naming and review
• Notes showing who agreed to what, with dates
• The date of the next milestone

Helpful context (optional)

• The assignment brief with its version and date.
• Team chat or meeting notes that show who accepted which task.
• A named person on the team who checks the result.

Tools and access

• A capable chat AI with file support: Reads the full pack and your notes. It can save the record file. In plain chat it returns the same tables as text.
• A chat AI that reads files, such as Claude, ChatGPT or Gemini: It reads the rubric and your notes together. In plain chat, paste the text in. No code or paid tool is needed.
• Any good chat AI: A one-message note works in any strong chat AI.

Functions and deliverables

• Capstone team agreement and handover reviewer: Keep your capstone team agreement current. Compare new commitments with the last review and get a task register and handover rules.
  • A list of what changed since the last review, with the source and date of each change
  • An updated team working agreement covering file versions, reviews, blockers and handover
  • A task register with an ID, owner, due date and status for each accepted commitment
  • A question list for tasks with no confirmed owner or date
  • A handover note, only if someone becomes unavailable, built from the real state of their work
  • A MISSING list, CHECKS MISSED and a short record for the next review
• Capstone team agreement planner: Share assignment rules, team time and agreed decisions. Get a team agreement, task list and handover rules.
  • A team working agreement with roles, file rules, review rules and handover rules
  • A task register with an owner, due date and status for each task
  • A list of tasks that still need an owner or a date
  • A note of anything your AI could not check
• Handover note writer: Turn a brain dump into a handover note. The person covering your work sees what breaks first and what is due, and can act on day one.
  • Time bombs first, each with a date and an action
  • What is due, live work with next steps, and where things live
  • The people and how to deal with them, what to leave alone, how to reach you
• AI session handover note writer: Finish or pause a chat. Get a short handover note with progress, open work, file references and suggested skills for the next session.
  • A one-page note with the goal, what is done and what is open
  • The first step for the next chat
  • Pointers to files and links, not copied text
  • A list of skills the next chat should use
  • A line confirming keys, passwords and personal details were left out
  Source: Matt Pocock.
• 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

• A team milestone is due and you want the agreement and task list checked against what people really accepted.
• The tutor or course changes the assignment rules, and your team agreement needs updating.
• Your team notes say "I'll do that", and you need to know which of those are firm commitments.
• A team member goes ill or leaves, and you need a handover note that lists their open work.

Limits to check before starting

• You are setting up the team agreement for the first time. Use the Capstone team agreement planner.
• You only need one person's handover written. Use the Handover note writer.
• You want an action list from one set of meeting notes. Use the Action item tracker keeper.
• You want to mark student work or judge who contributed what. Use the Student rubric feedback writer, and leave grades to the teacher.
• You want it to message your team or change a shared task board. It prepares drafts and takes no action.

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 agent pack and add it to Claude, ChatGPT or Gemini. Add the team agreement planner and the handover note writer from the pack too.
• Say if this is a first run. If not, paste your last review and its record.
• Attach the assignment rules, the team's availability, and the notes or chat where people agreed to work. Say the date of the next milestone.
• Read "Changed since last review" first. Check each change with the team member it names.
• Read the question list. Ask each person to confirm their tasks and dates, then add the answers and run it again.
• Share the agreement with the team only after everyone has read it. The agent sends nothing and assigns no one.

Read it as data

Read the complete role setup as JSON. Connect your AI to the AI Blocks MCP library and read aiblocks://roles/capstone-commitment-review-assistant 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.