Skip to content →

Month: December 2025

Basic Accessibility Gaps Still Too Common, Microsoft please justify CopilotNative.Chat.Controls

With the end of the year approaching, I was doing some tax prep. I asked the Windows version of Copilot to convert a final pay summary from my last employer into something that was more readable. To Copilot’s credit, it converted the PDF into a highly accessible Excel spreadsheet. That’s the positive. It is really handy.

Unfortunately, that’s not the full story. In reviewing the conversation, here is how the entry providing my answer reads with a screen reader. Note this is just the start of the answer.

CopilotNative.Chat.Controls.ViewModels.MessageThinkingAndActivityPartCopilotNative.Chat.Controls.ViewModels.MessageDocumentPartYour Excel spreadsheet is ready to go — you can **click the card above to download it**.

I have to ask why this sort of a basic accessibility failure is still making it to customers. Both automated and manual testing could easily find this sort of a failure and likely basic code inspection and automated checking as well at the code level.

People who do not use screen readers would never be shown text like CopilotNative.Chat.Controls and the rest of the long string those of us who do use such technology are offered. This is simply not acceptable.

Sadly, this is still far too often the reality of accessibility though in 2025. It is part of why I wrote my post on Accessibility island years ago at https://theideaplace.net/accessibility-island-the-journey-of-many-experienced-as-one/. It is also why I say the accessibility field, especially at the corporate level, needs to be far more accountable. I wrote about this also at https://theideaplace.net/from-word-fluff-to-real-impact-achieving-specific-measurable-and-accountable-accessibility/.

Some accessibility is more complex to address but these sorts of issues are not. All it takes is commitment and attention to the most basic of details.

If you try to reproduce this, the issue seems to occur when Copilot is producing downloadable content. Of course, the Windows Copilot app still serves at best half an answer to screen reading users in my opinion in general.

Yes, it is true that AI, as with many technologies, has done many innovative things for accessibility. But the full story should be positive, not just the innovations. These tools still need sizable attention because the basics of accessibility within many of these tools still falls short.

Leave a Comment

Image Description Toolkit 3.6.0 Available

A 3.6.0 release for my Image Description Toolkit is now available. The release features a new –redescribe option as well as support for two Microsoft Florence-2 models via Hugging Face.

Redescribe

The redescribe option can be used with the command line version of the toolkit to redescribe the same set of images without the need to extract video frames or convert image files to JPG from HEIC. This can save time and allow you to quickly test different prompts on the same set of images. To use the redescribe option, simply add –redescribe as the first option in an “idt workflow” command followed by the standard –provider, –model and –prompt-style options. Use the workflow directory from a previous image description workflow as the file directory for images to be described. Product documentation has full details.

Hugging Face and Florence Models

Hugging Face is described as “The platform where the machine learning community collaborates on models, datasets, and applications.” It contains a wide range of AI models, datasets and apps across the full spectrum of AI tasks.

The Florence-2 AI model is described in part as, “an advanced vision foundation model that uses a prompt-based approach to handle a wide range of vision and vision-language tasks.” It runs locally and requires no pre-installation. Note that the model will download on first use so expect a longer image description time. Also be aware that for a variety of reasons, the Florence-2 model is only supported in the command line version of the Image Description Toolkit.

You can get the latest update for the Image Description Toolkit from my projects page at www.theideaplace.net/projects or the GitHub release page.

2 Comments