Skip to content

Generative AI & LLMs

Copilot pattern

A design in which AI assists a human who remains actively involved in the task.

Example

An AI suggests code while a developer chooses and reviews changes.

Why people use it

It keeps a person actively involved while AI helps with parts of the work.

What you'll hear

“It suggests the next step; I choose whether to use it.”

What this means for you

Define which actions the human must review and approve.

Can you control it?

Sometimes

Sometimes. Your choices depend on the tool and your access. The settings available to an everyday user may differ from those available to the people running it.

Common questions

Is a copilot inherently less risky than an autonomous agent?
Risk depends on permissions, use and oversight, not the label alone.
Can the person become overly dependent on suggestions?
Yes. Repeatedly accepting them without thinking can weaken useful checking or practice.
Does the pattern require a chat window?
No. Suggestions can appear within an editor, form or other working interface.

Related terms

Still have questions?

Up to 500 characters.

Ask LATHIC about AI. Relevant glossary entries may be included.

Your question, the glossary entries it matches, and a rotating pseudonymous identifier go to Microsoft Azure’s OpenAI service through Vercel AI Gateway to generate an answer. Zero retention and no training are required of the provider, and LATHIC does not save your question or answer. Privacy Notice