SCS Advisory
Wealth management firm, Bellevue, Washington
- Size
- Not stated
- Where
- US
The job
A consultant built a compensation splitting application that runs on the operations lead own Windows PC using local Qwen models, with no cloud and no data leaving the machine. She types a rule change in plain English, the app updates the formula and the written rule together and shows her both to confirm, then runs the quarterly calculation in one click.
Tool: Custom Built (Qwen)
What happened
The firm saves about 200 hours a year on quarterly compensation calculations.
The work took a full week every quarter, and closer to a week and a half at year end. The local models answer in under a second, and the process rules are now written down as a readable rulebook where before they existed only in the head of one person.
Before you believe it
Prowess Consulting built the app and published the story, so the hours are the builder and client account. The saving rests on one person's process that was never written down, so the first job is documenting your own rules before any tool can run them.
Try this prompt
Test the job on your own material before buying anything. Replace the highlighted brackets.
Here is the written rule for how we split compensation: [RULE]. Change it as follows: [CHANGE]. Show me the rule before and after in plain English, the formula before and after, and one worked example using these figures: [FIGURES]. Do not apply the change until I confirm.
Source
Prowess Consulting ↗, 21 September 2026 · vendor story
This source was written or published by the supplier of the tool, so treat the claim as a sales story.
More from the archive
Mothership Coffee Roasters
Coffee roaster with six cafes, Las Vegas
The founder connected the till system, QuickBooks, Slack and email to Claude and made it the leadership team workspace for forecasting and weekly planning across six cafes plus wholesale and catering.
Result In-store margins rose to 22%.
Not statedUS
Russell Roof Tiles
Roof tile manufacturer, Burton on Trent and Lochmaben
The firm built its own internal AI tools over the past year. Operators record quality checks digitally from the factory floor with real-time performance data across two sites, staff query the ERP system directly to find priority orders, and month-end reporting tasks run automatically.
Result One month-end reporting task fell from 60 to 90 minutes to about three minutes.
About 160 staffUK
Reno Salvage
Salvage and scrap metal yard, Reno, Nevada
The operations manager uses ChatGPT to troubleshoot equipment faults as they happen, to look up specifications and materials for customer questions on the spot, and to build a part numbering system for the yard stock.
Result A part numbering system for over 1,000 items was built in a single afternoon.
Not statedUS
Keep browsing: more in Operations (14)
New entries every week
The archive grows weekly. Get the stories in your inbox, with the context behind them.