Asset Tagging & Physical Inventory

The problem this kills

It's count season again. You print the fixed-asset register, hand clipboards to a couple of people, and send them off to walk every floor and closet ticking boxes. A week later you're staring at three marked-up spreadsheets trying to figure out which assets nobody could find, which ones turned up that aren't on the register, and which laptop "moved" from Finance to the warehouse versus actually walked out the door.

Then comes the hard part: someone has to decide what to write off. What's the net book value of the missing projector? Did anyone actually approve disposing of it, or did it just quietly disappear from next year's register? When the auditor asks you to show the count sheets, the reconciliation, and the sign-off on every write-off, you're reassembling the story from memory and email.

Physical inventory of fixed assets is a process that looks simple and is secretly a governance minefield. This tool turns the clipboard-and-spreadsheet scramble into a clean, scan-by-location count, an automatic reconciliation, and an enforced approval gate before a single asset is written off or transferred.

What you'll build

A small internal web app, just for your team, that:

• Imports your asset register from a CSV (tag ID, description, location, cost, accumulated depreciation, net book value).
• Lets staff record counted assets by location from a phone or tablet - scan a QR or barcode on the tag, or type the tag ID, plus the location they found it in and its condition.
• Reconciles the counted assets against the register and flags every exception: missing (on the register, never counted), found (counted, not on the register), and moved (counted in a different location than the register says).
• Computes the write-off net book value for missing assets so the controller sees the real financial impact, not just a tag number.
• Routes every proposed write-off and location transfer to the controller for approval - the AI drafts the exception list, a person decides.
• Dedupes on tag ID so the same asset can't be counted twice (and warns if two people scan the same tag).
• Exports an updated register, a count report, and a set of write-off journal entries ready to hand to your accounting system.

What's inside the Implementation Plan

The plan is a single markdown file you paste into Claude Code (a free AI coding agent). It walks the agent through building the whole tool, step by step, each step ending with a ready-to-paste prompt.

The most important part: the plan opens by interviewing you about your business. Before it writes a single line, the agent asks how you run your count today, exactly what columns and codes live in your asset register, how your tag IDs and location codes are formatted, how many assets you have and how many sites, your rules for what counts as "missing enough" to write off, and your messiest edge cases (assets in transit, leased equipment, bulk-tagged items, components, an asset that was disposed but never removed from the register). It reads a short tailored spec back to you, you confirm it, and only then does it build - so you get a tool shaped to your register and your count process, not a generic template you have to fight.

Inside you'll find:

• The discovery interview and how the agent turns your answers into the data model.
• The full build: database, login, register import with duplicate guards, the mobile scan-by-location count screen, the reconciliation engine that classifies missing/found/moved, the NBV calculation, the controller approval queue, and the export step.
• The hard human-approval gate so no write-off or transfer is ever recorded without sign-off.
• Verification steps so you can prove it works, and the CSV-export fallback so it's fully usable even before you connect it to your fixed-asset system.

The governance it includes (this is the point)

This isn't a toy. The plan builds in the controls a finance team actually needs:

• Login so only your team can see or touch anything.
• Row-level security so people only ever see their own organization's assets and counts.
• A complete audit trail - every scan, every reclassification, every approval, every export is logged with who and when.
• A hard human-in-the-loop gate - the AI reconciles and drafts the exceptions, but the controller must review and approve every write-off and transfer; nothing is auto-recorded.
• Net book value computed before sign-off so disposals are approved with eyes open on the financial impact.
• Duplicate guards so the same tag ID can't be counted - or written off - twice.

Who it's for

Accountants, fixed-asset accountants, controllers, and ops staff who run periodic physical verifications of equipment and need them to be fast on the floor and airtight on paper - without hiring a developer or buying a heavyweight asset-management platform. You don't need to write code. You need your asset register CSV, a phone to scan tags, and an afternoon-to-a-weekend.

You've got this - paste the first prompt and let the agent interview you.