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 retail managers

Seasonal Buy Plan Agent

Build a seasonal buy plan, track early sell-through against it and adjust reorders and markdowns

Seasonal Buy Plan Agent: what goes in, what the agent does and what you get

What it does

Seasonal buys are placed months ahead and often miss. The agent builds a buy plan for each item from last season's sales, trends and weather signals, and sets quantities within the open-to-buy budget and supplier lead times. Once the season begins, it tracks sell-through each week against the plan. When an item runs ahead, it proposes a reorder if the lead time still allows. When an item runs behind, it checks price, placement and stock before proposing a markdown. It rechecks the effect the following week. The manager approves every purchase and markdown. Edge case: a cold spring cuts garden item sales by 30% in two weeks, and the agent proposes pulling forward a promotion.

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
ApprovedYes, continueApprovedYes, continueNoNo 1 STARTS WHEN Planning window opens 2 USES A TOOL Load last season sales, trends and weather outlook 3 DOES Compute a buy quantity per item within budget 4 YOU APPROVE Manager approves the buy 5 USES A TOOL Track weekly sell-through against the plan 6 CHECKS THE RESULT Is each item within 15% of plan? If not: Classify items as ahead or behind and find thecause. Back to step 5. 7 DOES Propose reorders for items ahead and markdowns foritems behind, after checking stock and placement 8 YOU APPROVE Manager approves reorders and markdowns 9 USES A TOOL Read sales the next week 10 CHECKS THE RESULT Did the action move sell-through back toward plan? If not: Adjust the reorder or markdown depth and proposeagain. Back to step 7. 11 RESULT Season report with plan versus actual
Read the steps as a list
  1. Planning window opens
  2. Load last season sales, trends and weather outlook
  3. Compute a buy quantity per item within budget
  4. Manager approves the buyThe agent waits here for your OK.
  5. Track weekly sell-through against the plan
  6. Is each item within 15% of plan?If not: Classify items as ahead or behind and find the cause. Back to step 5.
  7. Propose reorders for items ahead and markdowns for items behind, after checking stock and placement
  8. Manager approves reorders and markdownsThe agent waits here for your OK.
  9. Read sales the next week
  10. Did the action move sell-through back toward plan?If not: Adjust the reorder or markdown depth and propose again. Back to step 7.
  11. Season report with plan versus actual

How it decides

Buy quantities start from last season adjusted for trend and weather; weekly sell-through decides reorder, hold or markdown.

  • Reorder when sell-through is 15% ahead and lead time fits
  • Check stock and placement before marking down
  • Cap total buy at the open-to-buy budget
  • Start markdowns at 4 weeks before season end

Make it yours

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

  • Plan variance trigger (default 15%)
  • Weather source
  • Markdown schedule
  • Budget cap

What keeps you in control

It always asks you first

  • Manager approves purchases
  • Manager approves markdowns

Hard limits

  • Never place an order without approval
  • Never mark down before checking the cause

It stops when

  • Done: season closes with leftover stock within target
  • Stop: budget is exhausted

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 120 patio sets, the plan was 18 sold by week 4. Actual was 9. The agent found the item was out of the front display, so it proposed a placement fix before a markdown. The recheck showed 14 by week 6. It still proposed a 10% markdown for week 8, which the manager approved, and the season ended with 6 left.

More agents for retail managers