Hire an AI catering order change 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 confirmed order, with the source and date of each change
• A discrepancy table with the confirmed value, the new value and the difference
• Recalculated order totals, with any mismatch flagged
• A service checklist from the approved procedures and the new times
• A handover note for the service lead that shows what changed
• Owner questions, such as unapproved changes and unclear dietary details
• 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: The customer emails a new guest count, and you need to know what else it changes in the order and the invoice.

• Changed since confirmed order. Each change to headcount, time, menu or price, with its source and date.
• Discrepancy table. One row per changed item with the confirmed value, the new value, the difference and whether the change is approved.
• Order totals check. The order and quote totals recomputed with units, fees and rounding, and any mismatch.
• Service checklist. The order-to-service steps from your approved procedures, with the new times.
• Dietary lines. Each dietary or allergy requirement word for word, its named reviewer and whether it is confirmed or open. It never says a dish is safe.
• Service lead handover. What changed first, then what is due, so the person running service can act on it.

How the work is checked

• Every difference from the confirmed order is on the discrepancy table with a source, a date and an approval status.
• The recomputed total either matches the quote or the mismatch is shown.
• Every dietary line is copied word for word, has a named reviewer and a status, and no dish is called safe.
• A change that was only suggested is not treated as the order.
• 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 confirmed order. Reads the saved record if it belongs to this order, or sets a first baseline. Lists each new or changed source. If nothing changed, it says so and stops.
• Check the totals and the checklist. Runs the Catering order and service checker. It recomputes the order totals with units, fees and rounding, and writes the order-to-service checklist from your approved procedures.
• Hold dietary facts apart. Copies each dietary or allergy line word for word to your named reviewer. If one is unclear or the reviewer is not named, the affected dish stops and appears on the question list.
• Write the service lead handover. Runs the Handover note writer. It puts what changed first, then what is due, then who needs to know.
• Save and hand back. Saves the review 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 catering-order-change-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/catering-order-change-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 confirmed catering order, with its version and date
• The approved change, in the customer's own words, with its date
• Guest counts, event times and the delivery or setup times
• The customer's dietary and allergy requirements, copied exactly as given
• The quoted prices, fees and any approved extras
• The approved preparation procedures
• The name of the person who confirms dietary facts, such as the chef
• Your last review (optional on a repeat run)

Helpful context (optional)

• The confirmed order form and the quote, not a retyped copy.
• The customer's own wording for any dietary need.
• A named chef or dietitian who confirms dietary facts.

Tools and access

• A capable chat AI with file support: Reads the order, the emails and your procedures, and can save the record file. In plain chat it returns the same tables as text.
• Claude, ChatGPT or Gemini with file support: They can read the order and quote as pasted text or a spreadsheet and show every sum. Nothing here needs web access.
• Any good chat AI: A one-message note works in any strong chat AI.

Functions and deliverables

• Catering order change reviewer: Check a catering order change against the confirmed order. Get a discrepancy table, a service checklist and owner questions before service.
  • A list of what changed since the confirmed order, with the source and date of each change
  • A discrepancy table with the confirmed value, the new value and the difference
  • Recalculated order totals, with any mismatch flagged
  • A service checklist from the approved procedures and the new times
  • A handover note for the service lead that shows what changed
  • Owner questions, such as unapproved changes and unclear dietary details
  • A MISSING list, CHECKS MISSED and a short record for the next review
• Catering order and service checker: Check a catering order's counts and costs. Get a service checklist based on approved times and dietary needs.
  • A table of totals recalculated from your order and quote, with each mismatch shown
  • A discrepancy table with both values, the gap and the source of each
  • A service checklist from order to service, with timings
  • Diet needs copied word for word, with who must confirm them
  • Questions for the owner to settle with the customer or the kitchen
• 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
• Campaign change impact reviewer: Map which campaign assets break when an approved price, offer or claim changes. Get a repair order and release limits from your own files.
  • A list of each asset showing if it is affected, unaffected, unclear or not checked
  • The exact place where each old fact appears, including derived values
  • A repair order with the smallest edit, owner and check for each fix
  • A date line that keeps old and new results apart
  • A list of assets and approvals still missing
• 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

• The customer emails a new guest count, and you need to know what else it changes in the order and the invoice.
• The event start time moves, and the preparation and delivery times need rechecking.
• Someone edits a quoted price or fee, and you need the order total recalculated.
• A guest adds a dietary need, and you need it passed on word for word to the right person.

Limits to check before starting

• You are checking an order for the first time with no earlier version. Use the Catering order and service checker.
• You want the AI to confirm that a meal is safe for an allergy. It cannot. A chef or a dietitian must confirm every dietary fact.
• You only need to check invoice totals and nothing else. Use the Invoice totals checker.
• You want to write the kitchen's standard procedures. Use the Process and SOP writer.
• You want it to email the customer or the kitchen. It prepares drafts and sends nothing.

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 catering order checker, the invoice totals checker and the handover note writer from the pack.
• Say if this is a first run. If not, paste your last review and its record.
• Attach the confirmed order and the change. Paste dietary details exactly as given. Name the person who confirms them.
• Read the discrepancy table first. Check each change against the customer's message.
• Send every dietary line to your named reviewer. Do not start preparation for a dish with an open dietary question.
• Answer the owner questions and run it again. The agent sends nothing, so you send the handover 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/catering-order-change-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.