Skip to content

Completion

Also called Output, Generation

What is Completion?

The text or code that an AI model generates and returns in response to a user's prompt.

A completion is the final output from an LLM. It represents the model's statistical prediction of the most likely sequence of tokens that should follow the input prompt. Completions can be simple text answers, structured JSON payloads, or fully executable code blocks.

How it relates to Orbit

Apollo reads recent prompt completions to understand what an Orbit project has finished. See Apollo, the Co-pilot for details.

When you would use it

You handle completions in your code when receiving the response payload from an AI API endpoint.

Common operations

  • Generating a block of code based on a comment.
  • Returning structured JSON data to trigger an application workflow.

Related terms

Where this is taught

No learning path uses this term yet. Browse the Learning Atlas for guided sequences through related ideas.