What do the links at the top mean?

A link takes you to another page. The links at the top give you these choices:

  • Start here — follow the four short lessons from the beginning.
  • Everyday uses — find small, practical jobs you could try with AI.
  • AI tools — meet examples of outside AI apps and learn how to choose one.
  • Explore more — find news, detailed activities, and the separate children’s area.
Microsoft Copilot Studio

Copilot Studio’s November 12 model change: test a copy first

Microsoft lists November 12 for changes to some older Copilot Studio agent models. Check whether your setup is affected before the automatic move.

Sources checked 2026-11-03. Access and availability can change.

Check which model your helper uses

If your business uses a Copilot Studio agent, check its primary model before November 12. Microsoft’s retirement table lists GPT-4.1, GPT-4.1 Mini, GPT-5 Chat, GPT-5 Auto, and GPT-5 Reasoning on the Standard harness, with GPT Chat Latest as their planned replacement. [1]

An agent is an automated helper that can answer questions or perform tasks. Its primary model is the main AI guiding that work. Standard harness is Microsoft’s name for one system that runs its agents. Model settings for individual prompts are separate.

This is catch-up coverage. The model-selection page displays October 23 as its last update; we checked it November 3. It gives no exact changeover hour. [1]

Check exceptions before planning around extra time

Microsoft’s exception names GPT-4.1 and GPT-5 for tenants covered by FedRAMP, a U.S. federal cloud security program, and for environments outside the United States where data movement between regions is restricted. Check that note against your environment; do not extend it to every listed model. [1]

The table lists extensions of up to 30 days. Microsoft says continuing with retired models after an automatic upgrade requires turning on its “Continue using retired models” setting. Confirm that the option is available for your agent before relying on it. [1][2]

Our take

For the person maintaining an agent, the useful question is whether it still does the right job. Make a test copy and use fictional examples with known outcomes before changing a working automation.

For an email-routing helper, try a routine inquiry, an ambiguous request, and a message that should require human review. Check the chosen destination, the wording and format, and whether any action occurs before approval. Compare the whole sequence, including what happens when information is missing.

A fluent reply is only one part of a successful workflow. Record what passes, assign someone to resolve failures, and keep a way to pause the job. We reviewed Microsoft’s documentation; we have not tested or migrated a Copilot Studio agent.

Sources & further reading

Open the source to check the original wording and current availability.

This is a source-linked briefing, not a hands-on product review. Provider claims and outside evaluations are identified in the text.

Hey, I’m Patch.

Your little guide to this website.

Ask about an AI word or find your next small adventure.

New here? Try “Help me get started.”

Prepared explanations + site search. No live model. Your question stays in this browser. How Patch works.