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

New Item Performance Review Agent

Review each new item at 6, 13 and 26 weeks against forecast and similar launches, and recommend keep, fix or delist

DecisionsAnalysisSalesManagement
See how it worksGet access
New Item Performance Review Agent: what goes in, what the agent does and what you get

What it does

Weak new items stay on shelf for a year because nobody reviews them. At 6, 13 and 26 weeks the agent compares each new item's sales with the forecast and with similar launches. It checks whether distribution was complete and whether promotions ran as planned, because low sales may be a supply problem. It then recommends keep, fix or delist, with the evidence. If it suggests a delist, it rechecks the causes first, such as out-of-stocks or poor placement. It tracks agreed actions to the next review. The manager approves each decision. Edge case: an item sells 40% below forecast but was missing from half of stores, so the agent recommends a fix.

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, continueYes, continueApprovedNoNo 1 STARTS WHEN Review date arrives 2 USES A TOOL Pull sales, distribution and promotion data 3 DOES Compare sales per store with forecast and similarlaunches 4 CHECKS THE RESULT Was distribution and promotion as planned? If not: Adjust the comparison for the gaps and rerun.Back to step 2. 5 DOES Classify the item as keep, fix or delist candidate 6 USES A TOOL Test causes for weak items: stock, placement, price,awareness 7 CHECKS THE RESULT Do the causes explain the shortfall? If not: Check more data before recommending delist. Backto step 6. 8 DOES Write the recommendation with evidence 9 YOU APPROVE Manager approves keep, fix or delist 10 RESULT Item review record and next review date
Read the steps as a list
  1. Review date arrives
  2. Pull sales, distribution and promotion data
  3. Compare sales per store with forecast and similar launches
  4. Was distribution and promotion as planned?If not: Adjust the comparison for the gaps and rerun. Back to step 2.
  5. Classify the item as keep, fix or delist candidate
  6. Test causes for weak items: stock, placement, price, awareness
  7. Do the causes explain the shortfall?If not: Check more data before recommending delist. Back to step 6.
  8. Write the recommendation with evidence
  9. Manager approves keep, fix or delistThe agent waits here for your OK.
  10. Item review record and next review date

How it decides

The agent compares sales per point of distribution with similar launches; it will not recommend delisting until distribution and promotion causes are ruled out.

  • Compare against the average of the last five similar launches
  • Treat sales under 60% of forecast after adjustment as weak
  • Do not delist before week 13 unless supply was complete
  • Recommend a fix when a cause is operational

Make it yours

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

  • Weak threshold (default 60% of forecast)
  • Review weeks (default 6, 13, 26)
  • Number of comparison launches (default 5)
  • Report format

What keeps you in control

It always asks you first

  • Manager approves every keep, fix or delist decision
  • Manager approves supplier notices

Hard limits

  • Never delist without the manager
  • Never judge an item before checking distribution

It stops when

  • Done: decision approved and logged
  • Stop: data for the item is 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 happensA new sauce was forecast at 5 units per store per week and sold 2.9 at week 6. The agent's first read said weak, but its check found the item was out of stock in 38% of stores. After adjusting, it was 4.1, so the recommendation was fix. At week 13 the item hit 4.6, and the manager approved keeping it.

More agents for category managers

Decisions · Planning

Operating Vendor Negotiation Prep Agent

Give the director a negotiation plan where each target and fallback is backed by data.

11 steps1 check10 jobs
Planning · Sales

Inventory-Linked Promotion Planner Agent

A promotion plan limited to items that have stock and keep margin

11 steps2 checks5 jobs
Monitoring · Reporting

Supplier Delivery Scorecard Agent

Supplier performance measured and improved

9 steps2 checks12 jobs
Decisions · Operations

Excess and Obsolete Inventory Review Agent

Excess stock is found early and turned back into cash

8 steps1 check14 jobs