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.