Complete AI Training
Sign inGet my AI kit

Your job's AI kit

Get your AI kit

Tell us who you are and what you do. We show you your kit right away and email you the link: skills, prompts, AI agents, MCP servers and courses for your job.

500+ jobs ready, and we make a kit for any other job. No payment needed to look.

Share

AI agent for restaurant managers

Weekly Food Cost Variance Agent

Food cost gap found and explained weekly

Weekly Food Cost Variance Agent: what goes in, what the agent does and what you get

What it does

Actual food cost often runs above theoretical cost, and nobody finds out why before the next week starts. This agent compares the week's actual food cost from inventory counts and purchases with theoretical cost from sales and recipes. It breaks the gap down by item and ranks items by dollar impact. For the biggest gaps it checks invoice prices, waste logs and count errors in turn. If a count looks wrong, it asks for a recount before blaming the kitchen. A supplier price rise shows as variance until recipes are updated, so it flags recipe costs to update. It drafts a short report with likely causes and actions. The manager approves actions such as portion training or a supplier call.

How it works

Follow the arrows from top to bottom. The orange dashed arrow is the loop: when a check fails, the agent goes back and tries again.

Start and resultWhat it doesA check on its own workWaits for your OKGoes back and retries
Yes, continueApprovedNo 1 STARTS WHEN Weekly count done 2 USES A TOOL Calculate actual and theoretical use 3 DOES Rank items by gap 4 CHECKS THE RESULT Are counts for top items believable? If not: ask for a recount. Back to step 2. 5 USES A TOOL Check invoice prices and waste logs 6 DOES Draft causes and actions 7 YOU APPROVE Manager approves actions 8 RESULT Weekly food cost report
Read the steps as a list
  1. Weekly count done
  2. Calculate actual and theoretical use
  3. Rank items by gap
  4. Are counts for top items believable?If not: ask for a recount. Back to step 2.
  5. Check invoice prices and waste logs
  6. Draft causes and actions
  7. Manager approves actionsThe agent waits here for your OK.
  8. Weekly food cost report

How it decides

It ranks items by dollar gap between actual and theoretical use.

  • Gap over set percent is flagged
  • Recount when change is unusual
  • Update recipe costs when prices change

Make it yours

Every agent is a starting point. You choose these settings for your own situation.

  • Variance threshold
  • Items tracked
  • Report day

What keeps you in control

It always asks you first

  • Actions

Hard limits

  • Never accuses staff

It stops when

  • Done: report done
  • Stop: count missing

Set it up

We guide you through the set-up, step by step

Members get the full set-up guide for this agent. No technical skills needed: you copy, paste and upload.

10 minto set it up in your AI
5 AIsChatGPT, Claude, Copilot, Gemini, Grok
  • One set of instructions to paste into your AI, with the clicks for ChatGPT, Claude, Microsoft 365 Copilot, Gemini and Grok
  • The agent then walks you through connecting your own data, one source at a time
  • A downloadable copy with the flow chart, the rules and the full guide
Get access to this agent

An example run

What happensWeek 32 food cost was 33% against a 29% target. Chicken was 40 pounds over theoretical. The agent checked prices, which matched. The count check failed at first because the freezer count was missing, so it asked for a recount, which confirmed the gap. The waste log showed none, so it suggested a portion check. The manager found portions 1 ounce over.

More agents for restaurant managers