Skip to content

Conversation

@eshentials
Copy link
Contributor

Summary

This PR updates the Workers AI Prompting documentation to clarify usage of the
assistant role in scoped prompts:

  • Added detail on which models are more likely to support it (chat-based vs instruct).
  • Explained safe behavior when unsupported (ignored).
  • Strengthened recommendation to use scoped prompts for consistency.

Closes #24816

Documentation checklist

  • Changelog entry — N/A (clarification only, not a new feature)
  • The documentation style guide has been adhered to.
  • Larger change issue — N/A
  • Redirects — N/A

@github-actions github-actions bot added product:workers-ai Workers AI: https://developers.cloudflare.com/workers-ai/ size/s labels Aug 30, 2025
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

product:workers-ai Workers AI: https://developers.cloudflare.com/workers-ai/ size/s

Projects

None yet

Development

Successfully merging this pull request may close these issues.

Workers AI Prompting: assistant messages as an output hint?

6 participants