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 category managers

Weekly Category Sales Review Agent

A weekly category review explaining sales and margin changes

Weekly Category Sales Review Agent: what goes in, what the agent does and what you get

What it does

Each week category managers review sales, margin and share by product, and digging through reports to explain changes takes hours. When the weekly data is ready, this agent pulls sales, margin, stock and promotion data. It first checks that data is complete for every store. If a store is missing, it marks the store and leaves it out so totals are not distorted. It compares results with last year and plan and splits each change into price, volume and mix effects. It then checks whether out-of-stocks or promotions explain the change, looking at lost sales from empty shelves first. It drafts the weekly review with suggested actions, such as fixing replenishment for a store. The category manager approves actions before they go to other teams. Edge case: a new product launch shifts sales from older ones, so the agent shows the net effect on the category.

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 data ready 2 USES A TOOL Pull sales, margin, stock and promotions 3 CHECKS THE RESULT Is data complete for all stores? If not: mark missing stores and exclude. Back to step 2. 4 DOES Break down change into price, volume and mix 5 DOES Check stock and promotion effects 6 USES A TOOL Draft review with actions 7 YOU APPROVE Category manager approves actions 8 RESULT Review shared
Read the steps as a list
  1. Weekly data ready
  2. Pull sales, margin, stock and promotions
  3. Is data complete for all stores?If not: mark missing stores and exclude. Back to step 2.
  4. Break down change into price, volume and mix
  5. Check stock and promotion effects
  6. Draft review with actions
  7. Category manager approves actionsThe agent waits here for your OK.
  8. Review shared

How it decides

It breaks changes into price, volume and mix and checks for stock or promotion causes.

  • Out-of-stocks explain lost sales first
  • Cannibalization shown as net
  • Missing stores excluded

Make it yours

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

  • Metrics
  • Breakdown
  • Report format
  • Day

What keeps you in control

It always asks you first

  • Actions
  • Price changes

Hard limits

  • No price changes made
  • Data shared internally only

It stops when

  • Done: shared
  • Stop: data 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 data arrives on Monday for the snacks category. The completeness check fails: 6 of 140 stores have no sales loaded. The agent waits for the reload and pulls the data again at noon. Sales are down 4.2%. The agent splits this into price minus 1.1, volume minus 2.6 and mix minus 0.5. It links the volume drop to an out-of-stock on a top chip line. The category manager approves a reorder action.

More agents for category managers