ABC Velocity Slotting Recommender
Build an internal tool that classifies your SKUs A/B/C by pick frequency, spots fast movers stuck in hard-to-reach slots, and produces a manager-approved, capped move worklist you can hand to the floor.
A login-protected web tool that ingests pick history, classifies SKUs A/B/C, compares them against current slots, proposes a capped set of moves with an effort estimate, lets an ops manager approve a subset, and exports a clean relocation worklist as CSV.
Before you start
- A pick-history export (CSV or Google Sheet) - which SKU was picked, when, and how often
- Your current slot assignments (which SKU lives in which location today)
- A ranking of your locations by accessibility (golden zone vs overflow)
- Free accounts for Vercel, Supabase, and Resend
The problem this kills
Your fastest movers are buried in the back, and your slowest movers are sitting in the easiest, most valuable slots. Pickers walk miles they shouldn't. Everyone "knows" slotting is wrong, but nobody has the hours to rank every SKU by pick frequency, cross-check it against where things actually live, and turn that into a move list the floor will actually execute.
So nothing changes. The spreadsheet someone started six months ago is stale. The re-slot project keeps slipping. And every shift quietly pays the tax in extra steps.
What you'll build
A small, private web app for your team that does the boring math and hands you an actionable plan:
- Upload your pick history and current slots (CSV or Google Sheet - no integration needed).
- It classifies every SKU into A / B / C by pick velocity, the way an inventory engineer would.
- It compares each SKU's velocity class to how good its current location is, and flags mismatches: A-movers stuck in overflow, C-movers hogging the golden zone.
- It proposes specific moves, respects item size and zone constraints, and caps the number of moves per cycle so the plan is something a crew can finish.
- An ops manager reviews the proposed moves and approves the subset to do this cycle - nothing is "official" until a human says so.
- It exports the approved moves as a clean relocation worklist CSV your WMS or floor team can run with.
What's inside the Implementation Plan
A complete, paste-and-go runbook for Claude Code. It is written for a non-coder: plain language, one step at a time, with a ready-to-copy prompt at the end of every step.
Most importantly, the plan opens by interviewing you about your warehouse - your pick-history format, your location naming, how you define the golden zone, your size and zone rules, your typical and peak move volumes, and your weird exceptions. It reflects a short tailored spec back to you for a thumbs-up, then builds the tool around your data and your rules instead of a generic template.
Inside you'll find: the discovery interview, the data model, the ABC classification logic, the slot-fit comparison, the move-cap and constraint rules, the manager approval gate, the CSV export, and a verification checklist so you know it actually works.
The governance it includes (this is the point)
This isn't a throwaway script. It's an internal tool with the controls ops leadership expects:
- Login so only your team can open it.
- Row-level security so each organization only ever sees its own data.
- A full audit trail - who uploaded what, who approved which moves, and when.
- A hard human-in-the-loop approval gate - the tool drafts the move list; an ops manager reviews and approves before any relocation work order is issued. The AI never commits a move on its own.
- Duplicate guards so the same SKU-and-move can't be slipped into the worklist twice.
Who it's for
Warehouse engineers, inventory control analysts, and operations managers who own slotting and putaway - and who want a real tool this weekend, not another stalled spreadsheet.
You've got this. Open Claude Code and paste the first prompt.