OneRange

What's New in Microsoft Copilot for Developers

A short refresher on the latest GitHub Copilot and Microsoft Copilot updates for developers

What this course covers

The course runs across 7 topics, each one a short adaptive session rather than a recorded lecture. The tutor explains the idea, works an example, checks understanding, and adjusts the next step to the answer given.

  • One Copilot cloud session you can pick up anywhere — What's different: Copilot now runs your tasks in a cloud workspace that you can start on github.com and pick up again in VS Code, GitHub Mobile, Slack or Teams. Why it matters for your work: You can hand off a task, walk away, and check or steer it later from whatever device you have. Try it (about 2 minutes): On github.com, open the Copilot page, give Copilot a small task in one repository, then open the same session from your editor's agents view or the GitHub Mobile Copilot tab. No access? Here's what you'd see: A Copilot cloud session started on github.com can be opened in the editor's agents view or the GitHub Mobile Copilot tab.
  • Auto model choice now has three settings — What's different: When you pick Auto as your model, you can now tell it to favor low cost (efficiency), a mix (balance), or best quality (intelligence). Why it matters for your work: You can let Copilot pick the model for you and still steer it toward speed for small jobs or quality for hard ones. Try it (about 2 minutes): In VS Code Copilot Chat, open the model picker, choose Auto, switch between the efficiency, balance and intelligence options, and ask the same question twice to compare. No access? Here's what you'd see: When choosing the Auto model in VS Code Copilot Chat, users see three settings: efficiency, balance, and intelligence.
  • Copilot Fusion picks and combines models for you — What's different: A new Fusion choice in the model picker lets Copilot choose and combine models for each task, with Standard, High and Max effort levels. Why it matters for your work: You no longer need to know which model is best; you pick how hard Copilot should work instead. Try it (about 2 minutes): In VS Code chat, open the model selector, choose Fusion, set the effort to Standard, and ask Copilot to explain one file in your project.
  • Copilot Memory remembers your preferences — What's different: Copilot Memory is now generally available on paid plans, so Copilot keeps your preferences and repository habits across sessions and tools. Why it matters for your work: You stop repeating the same instructions, and you can see and delete what Copilot has saved. Try it (about 2 minutes): In Copilot chat, tell Copilot one preference to remember, such as how you like pull request descriptions to start, then open your Copilot settings to view or delete it. Needs: paid plans.
  • Assisted permissions approve safe actions for you — What's different: A new Assisted permission mode, now generally available in VS Code, Copilot CLI and the Copilot app, uses AI to auto-approve clearly safe commands, file access and URLs, and still asks you about the rest. Why it matters for your work: You get fewer pop-ups during agent work while risky actions still need your OK. Try it (about 2 minutes): In VS Code, open the permissions picker in the chat box and select Assisted permissions (in the CLI, run /permissions and choose assisted), then give the agent a small task. No access? Here's what you'd see: An "Assisted permissions" option appears in the VS Code chat box permissions picker, and an "assisted" option appears in the CLI.
  • Also new — - Code review says if a pull request is ready to approve: Copilot code reviews now include an approval assessment to indicate if a PR is ready. - Copilot harness becomes the VS Code default; Ask is back: VS Code defaults to the Copilot harness and returns Ask to the agent picker. - Redesigned model picker in VS Code: The VS Code model picker is redesigned with separate tabs and hover settings for thinking levels. - Several older GPT, Gemini and Grok models retired: Several older GPT, Gemini, and Grok models were retired from Copilot on October 19. - Watch and fix keeps pull requests ready to merge: A new Watch and fix button lets Copilot automatically resolve failing checks and merge conflicts. - Ask Copilot to make or edit images (preview): Copilot chat in VS Code can now create, edit, and save images from plain-English requests. - Connect Slack, Notion and more in one click (preview): GitHub-checked connectors let you link external services like Slack and Notion to Copilot in one click. - Local sandboxing limits what agents can touch: Local sandboxing is now available to restrict agent access to files, networks, and credentials. - Copilot can use desktop apps (preview): Copilot can now interact with desktop apps on macOS and Windows after user approval. - Plugin registry and Work IQ Developer Tools: Developers can package and publish plugins using the new Work IQ Developer Tools and plugin registry. - and 12 more: Federated connectors bring live outside data into Copilot; Personal settings page for Copilot code review; A new Claude Opus model in the model picker; Hand work to Copilot from Slack (preview); Start cloud agent automations with a comment; Code review adds a Max setting; approvals now final; Clearer code review summary and commit messages; Minimize and resume Copilot Chat on github.com; Shared Copilot Automations for whole teams; GitHub Copilot SDK becomes Microsoft Copilot SDK; Code review now uses Balanced effort by default; Copilot Studio: GitHub Copilot harness is ready
  • Try one on your own work — Pick the one main change from this course that is most useful to your job. Try it in your own Microsoft Copilot on a real task, then paste or describe what you got. The coach gives short, specific feedback. No access to the app or plan it needs? Describe how you would use it on a real task this week. That counts too. There is no score and no pass or fail: finishing this completes the course.

Skills you build

Results are measured against named skills in the OneRange taxonomy of more than 10,000 skills, so a manager sees proficiency per skill rather than a completion tick.

Who it is for

The material is pitched at intermediate level, and takes roughly 20 minutes at a typical pace. Because every session adapts, someone who already knows a topic moves through it quickly instead of sitting through an explanation they do not need.

It sits in the Tool: Microsoft Copilot track of the Vero AI Catalog, and can be assigned to one person, a team, or the whole company.

How it is delivered and assessed

Delivery is conversational and interactive. There is no video to sit through and no slide deck to click past.

Understanding is checked with a lab assessment, with a pass mark of 70%.

Administrators can copy this course into their own library and adapt it — edit the outline, change the duration, swap the assessment format, or ground it in internal documentation so answers cite the company's own source material.

Also in this track

Related

Frequently asked questions

How long does this course take?

It runs roughly 20 minutes at a typical pace. Because every session adapts, someone who already knows a topic moves through it quickly instead of sitting through an explanation they do not need.

How is it assigned to a team?

An administrator assigns it from the Vero dashboard to one person, a team, a department or the whole company, and sees progress and results per person and per skill.

Can we customise it with our own documents and terminology?

Yes. Administrators can copy this course into their own library and adapt it — edit the outline, change the duration, swap the assessment format, or ground it in internal documentation so answers cite the company's own source material.

Course code what-s-new-in-microsoft-copilot-for-developers-e424c0ab.