HT @The_Alex for the inspiration xitter.cf/The_Alex/status/209596…
great work from the Stark team
Stark Designer accessibility agent 😻
github.com/stark-contrast/sk…
for posterity, there's also City Lights, OG accessibility fixtures 😎 w3.org/WAI/demos/bad/after/h…
Replying to @feather
tear downs are hard; they require an existing app and ideally source code. That leaves you either working with open source apps or building your own fixtures. agents make it a lot easier to generate sample sites (see github.com/AccessLint/demo), but its more contrived.
excited about how #WebMCP can make canvas content more accessible to screen reader users. combining accessible markup with an agent makes working in a canvas better for everyone, and helps out blind users especially.
youtube.com/watch?v=F-HO5xBw…
Replying to @0xidanlevin @OpenAIDevs
have you tested the extension against gpt-5.6-terra? I get 400s on the openai completions endpoint not supporting reasoning effort for terra. same issue in the webmcp-evals CLI: github.com/GoogleChromeLabs/…
opened an issue for chat tool calls here, in case its an actual missing feature / bug: github.com/vercel-labs/agent…
Replying to @ctatedev
very cool! are you using chat in that demo? chat is refusing to do tool calls for me.
I stood up an example of how you can pair WebMCP with an accessible canvas application to help agents and assistive tech users work together.
Video shows me navigating a flow diagram in the ChatGPT browser and prompting the agent to create new keyboard accessible diagrams from text and from a screenshot.
How can folks get in the EAP for WebMCP support in Gemini in Chrome / Ask Gemini? Trying to do UXR a screen reader user and have higher confidence in a Chrome-based experience being familiar and accessible. @sarah_edo ?







