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

Assortment Range Review Agent

A range plan that improves sales per space

Assortment Range Review Agent: what goes in, what the agent does and what you get

What it does

Range reviews decide which products to keep, add or delist, and cutting the wrong item loses loyal customers. When the review cycle starts, this agent pulls product data and ranks every product by sales, margin and how often customers would switch to another product if it were removed. It flags the bottom 10 percent for review and finds gaps where demand is not met. Before suggesting a delisting, it checks whether the product is unique for a customer group. If removing it would lose those customers, it keeps the product and looks at the next candidate. It then models the new range against shelf space and category margin. The category manager approves all range changes and any talks with suppliers. Edge case: a slow product required by a supplier contract is marked as fixed and stays in the range until the contract allows a change.

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 Review cycle starts 2 USES A TOOL Pull product data 3 DOES Rank products and find gaps 4 CHECKS THE RESULT Would delisting lose unique customers? If not: keep the product and re-rank. Back to step 3. 5 DOES Model new range on space and margin 6 YOU APPROVE Category manager approves changes 7 RESULT Range plan issued
Read the steps as a list
  1. Review cycle starts
  2. Pull product data
  3. Rank products and find gaps
  4. Would delisting lose unique customers?If not: keep the product and re-rank. Back to step 3.
  5. Model new range on space and margin
  6. Category manager approves changesThe agent waits here for your OK.
  7. Range plan issued

How it decides

It ranks products and protects unique items.

  • Bottom 10% reviewed
  • Unique items protected
  • Contracts respected

Make it yours

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

  • Delist threshold
  • Uniqueness rule
  • Space rules
  • Review cycle

What keeps you in control

It always asks you first

  • Range changes
  • Supplier talks

Hard limits

  • No supplier contact
  • No contract changes

It stops when

  • Done: plan issued
  • 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 happensFor the spring review of 220 pasta sauce items, the agent ranks products and suggests delisting 18. The check fails for 3 of them: loyalty data shows 9% of their buyers buy no other sauce. The agent keeps those 3 and finds 2 more weak items instead. It models the new range on shelf space and margin, showing a 1.8% margin gain. The category manager approves the changes on March 3.

More agents for category managers