The SmallOffice Brief Subscribe
Money, Bills & Benefits
Sat, Nov 14, 2026
Claude Code

2,047 invoices daily, 94.3% untouched

A small chartered-accountancy firm in Gurgaon took in more than 2,000 vendor invoices a day in a shared Drive folder. Three junior accountants spent six hours each keying them into Tally. That data entry cost about 180,000 rupees a month in salary. The builder set three Claude Code sub-agents under a small Python orchestrator on a 15-minute cycle. One pulls the vendor name, tax ID, line items and totals from each PDF as structured data. One checks the tax math and matches the vendor master. One posts clean records to Tally and returns the voucher number. Moving the checking step to a smaller model cut the cost per invoice from 0.40 rupees to 0.06.

How it wentIn week one the system averaged 2,047 invoices a day. It posted 94.3% with no human touch. The other 5.7% went to an exception queue, mostly scanned PDFs with poor OCR. Compute ran about 840 rupees a day across all three agents, against about 180,000 rupees a month of manual effort. The builder puts payback at about two weeks. A later prompt fix for handwritten delivery notes dropped the exception rate to 3.1%. The firm is not named, and the report is the builder's own.
Try it · based on the source's workflow
Extract the structured data from each [invoice] PDF I name. Return one JSON object only, no prose and no markdown fences. Fields: vendor name, [tax ID], invoice number, invoice date, line items with [item codes], each tax line, and the total. If the [tax ID] is missing or fails its format check, return {"error": "invalid_tax_id"} instead. Show me any invoice you cannot read clearly before you post it anywhere.
A starting template based on the workflow the source describes. Review it before you use it; you are responsible for what it does.
ShareXLinkedInForward to a friend
Cite this case2,047 invoices daily, 94.3% untouched. The SmallOffice Brief, Sat, Nov 14, 2026. https://smalloffice.space/case-2-047-invoices-daily-94-3-untouched
Share this win
2,047 invoices daily, 94.3% untouched — from The SmallOffice Brief, a daily brief of real AI cases for small businesses: https://smalloffice.space/case-2-047-invoices-daily-94-3-untouched
One bot, one job

Start with one job only. Fill in the three lines. Keep the bot on that job.

The one job this bot does: ______________________________

What it may do on its own: ______________________________

What it must ask me first: ______________________________

Before and after

Two lines from this case, side by side. No new figures.

Before · as the case describes it

A small chartered-accountancy firm in Gurgaon took in more than 2,000 vendor invoices a day in a shared Drive folder. Three junior accountants spent six hours each keying them into Tally. That data entry cost about 180,000 rupees a month in salary. The builder set three Claude Code sub-agents under a small Python orchestrator on a 15-minute cycle. One pulls the vendor name, tax ID, line items and totals from each PDF as structured data. One checks the tax math and matches the vendor master. One posts clean records to Tally and returns the voucher number. Moving the checking step to a smaller model cut the cost per invoice from 0.40 rupees to 0.06.

After · as the source reports it

In week one the system averaged 2,047 invoices a day. It posted 94.3% with no human touch. The other 5.7% went to an exception queue, mostly scanned PDFs with poor OCR. Compute ran about 840 rupees a day across all three agents, against about 180,000 rupees a month of manual effort. The builder puts payback at about two weeks. A later prompt fix for handwritten delivery notes dropped the exception rate to 3.1%. The firm is not named, and the report is the builder's own.

The after line is the source's claim, not our measurement.

smalloffice.space · Get a case like this in your inbox each morning. Subscribe free

Send this case to my inbox

Read this case on your phone now, and keep it for later. Type your email. We send this case to that address, and you get the next cases each morning too.

Additional Details

Published: Sat, Nov 14, 2026 · Updated: Sat, Nov 14, 2026 · Topic: Money, Bills & Benefits · Tool: Claude Code · Source: dev.to (Archit Mittal)
Next case: Nine screening calls, booked overnight. Get cases like this in your inbox each morning.
5 cases in your inbox each morningSubscribe free