Urgent.News

What's breaking now, across hundreds of outlets.

AI

Reconciling two Excel workbooks offline with a local Windows AI assistant

What should a local language model do when a user asks, “What changed in these two spreadsheets?” A plausible answer is easy to produce. A result that survives a row reorder and points back to both source cells takes a different implementation. In OSTUM Desktop, the chat routes that request to a local workbook reader. The user chooses the original file, the revised file and a key column on each…

When a user inquires about changes between two Excel workbooks, a local language model can provide a clear answer. OSTUM Desktop facilitates this process by routing the request to a local workbook reader. The user selects the original file, the revised file, and a key column on each sheet. The model retrieves a price, such as 90 or 100, directly from the spreadsheet cells, and does not need to infer the price from text.

To demonstrate the functionality, two downloadable workbooks with the same sheet named "Прайс" (price list) were used. Column A contains product codes, while column B lists prices. In row 2, the product code A17 shows a price change from 90 to 100 RUB. Checking both files, B2 contains the corresponding price.

In the original file, row 42 (D42) was removed. In the revised file, row 53 (E53) was added. Additionally, products B24 and C31 exchanged positions, but their values remained unchanged. Running these files through the 5.7.0 comparison engine yielded three differences. A row-by-row comparison would also report changes for the two moved products.

The review window presents the old value, the new value, and both source addresses. After generating the report, the operation verifies the revisions of the input files before writing. If a source is modified after the preview, the comparison must be refreshed. Weekly reports can be automated by creating a named recipe that specifies which sheets and key columns to use. The next run will prompt the user for a fresh pair of files, allowing the user to review changes without maintaining a folder of hard-coded source paths.

The two sample XLSX files can be downloaded and a walkthrough provided. The Windows interface is in Russian, but an English guide outlines the necessary controls. Basic local chat is free and does not require an account. The Excel workspace is a Pro feature that requires a one-time purchase of a subscription to the developer's Telegram channel. The app code is MIT-licensed, and the source and Windows release is a maintainer article prepared with AI assistance.

Rewritten by urgent.news; may contain errors — check the original.

Read the original at dev.to →

Report a problem with this story

More in AI

From task.md to Orca: How I Streamlined My Claude Code and Codex Workflow

In a previous article, How I Use Claude Code and Codex Together to Build .NET Features Faster , I described a workflow in which Claude Code and codex linked together to achieve my codings tasks.

  • Orca replaces task.md in Claude Code workflow
  • Orca uses repository as project exploration space
  • Orca streamlines workflow by reducing setup time

AI Coding Agents Raised Commits 240%. Releases Rose Only 30%

Autonomous coding agents lifted commit volume 240% across more than 500,000 GitHub developers, yet software releases rose only 30% (Source: National Bureau of Economic Research, 2026).

  • AI coding agents caused a 240% increase in code commits across GitHub users.
  • Software releases only rose by 30% in the same period.
  • 20.7% of Philippines working-age individuals use generative AI products.

More from Saturday 21 November →