Introduction
I came across Copilot Keyboard, a keyboard app from Microsoft, in the Microsoft Store and gave it a try. It supports cloud-assisted predictive conversion, and its selling point is that it covers new words and trending terms too.
Installation
Open the Microsoft Store and type “Copilot Keyboard” into the search box. When the app shows up, click Get to download and install it.
Initial Setup
When you launch the app, a setup screen appears. There are two main settings.
Turn Off Diagnostic Data Sharing
I turned off “Share diagnostic data to help improve Windows products.” This setting sends usage data to Microsoft, and if you care about privacy, it’s fine to leave it disabled.
Turn On Cloud Suggestions
Turn on “Use cloud suggestions to show the latest words as predictive conversion candidates.” This feature draws on data in the cloud to include new words and trending terms in the conversion candidates, and enabling it is really the whole point of the app.
Once you’ve set these, press Start and setup is complete.
Summary
- You can get Copilot Keyboard from the Microsoft Store
- I turned off diagnostic data sharing, turned on cloud suggestions, and started using it
- Cloud suggestions bring the latest vocabulary into predictive conversion, which is handy
I’m going to keep using it for a while!
Related Posts
I Looked into Using the Host's Local LLM from WSL, and Decided Not To
I wanted to use the local LLM on my Windows host as a reviewer for development in WSL. There are two routes, and either one can be made to work. But one meant giving up safety and the other meant giving up reliability, so I passed. This is a record of that decision.
How I Made the Local LLM on My Ryzen AI PC 7 Times Faster (llama.cpp + Vulkan + Qwen)
I rebuilt the local LLM setup on my freshly wiped Ryzen AI 9 HX 370 machine with llama.cpp and Vulkan: about 7 times faster than CPU inference. Here's how picking the newest model backfired, and measurements showing the bigger file was faster.
Wiping the Local LLM Setup on My Ryzen AI PC Clean
To rebuild the local LLM setup I had piled up on my AMD Ryzen AI 9 HX 370 machine with the latest approach, I'm deleting it all first. I cover taking inventory of what's left, the removal steps, and what you shouldn't delete.