Skip to main content

AI Usage > Suggestions rejected

Written by Tom Williams

Dataset: AI Usage

Entity: AI Usage Measurement

Field ID: suggestions_rejected

Type: Number

Description: The number of AI suggestions that were explicitly rejected.

Not published by GitHub Copilot. This measurement is empty on GitHub Copilot records. It is populated by Claude Platform, and by Cursor once it is released.

Source: App

Transformation logic: N/A

App Mapping

GitHub Copilot

N/A

Claude Platform

the sum of rejected actions across all editing tools

Cursor (coming soon)

totalRejects

OpenAI Platform

N/A

OpenAI Codex Enterprise

N/A

Reporting Use Cases

The Suggestions rejected field counts explicit rejections, as opposed to suggestions that were simply ignored.

  • Acceptance rate where no offered count exists: For Claude Platform records, compute acceptance as SUM(suggestions_accepted) / (SUM(suggestions_accepted) + SUM(suggestions_rejected)).

  • Quality signal by model: A rejection rate that rises after a model change is a concrete signal worth acting on.

  • Rejected is not ignored: Only explicit rejections are counted. Suggestions that were never acted on appear in neither this field nor the accepted count.

Did this answer your question?