Require Moonbeam to pick a winner on comparative/winner questions#249
Merged
Conversation
Copilot
AI
changed the title
[WIP] Update Moonbeam's participation tagging logic for clear decisions
Require Moonbeam to pick a winner on comparative/winner questions
May 11, 2026
There was a problem hiding this comment.
Pull request overview
This PR updates Moonbeam’s system prompt (used by the backend participation flow) to explicitly require a decisive winner/pick-a-side answer when users ask comparative or winner-related questions, and adds unit tests to lock that requirement in.
Changes:
- Added a new response strategy rule requiring Moonbeam to name a winner / pick a side (no ties or hedging).
- Extended the
<verification>checklist with an explicit “winner questions must name a winner” check. - Added tests asserting the new winner-decision rule and verification checklist item are present.
Reviewed changes
Copilot reviewed 2 out of 2 changed files in this pull request and generated 1 comment.
| File | Description |
|---|---|
| packages/backend/src/ai/ai.constants.ts | Adds winner/pick-a-side rule to Moonbeam instructions and a corresponding verification checklist item. |
| packages/backend/src/ai/ai.constants.spec.ts | Adds tests asserting the winner-decision rule and verification checklist item are included in the prompt constant. |
💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.
|
|
||
| two people arguing → state your position directly and support it with reasoning. avoid vague neutrality. | ||
|
|
||
| asked who won, who's winning, who's better, did someone win, or any request to pick a side or declare a winner → pick one. name a winner, declare a clear preference, or state an unambiguous judgment. do not give a tie, "both have merit," "it depends," or any non-committal answer. if you genuinely cannot tell from context, make your best call and commit to it. |
sfreeman422
approved these changes
May 11, 2026
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Moonbeam was giving non-committal, fence-sitting responses when asked winner-related or comparative questions ("who's winning?", "did I win?"). The participation tagging logic needed an explicit directive to force a decisive answer.
Changes
ai.constants.ts—MOONBEAM_SYSTEM_INSTRUCTIONS<response_strategy>rule: when asked who won, who's winning, who's better, or to pick a side, Moonbeam must name a winner or declare an unambiguous preference — no ties, no "both have merit," no "it depends"ai.constants.spec.tsMOONBEAM_SYSTEM_INSTRUCTIONSOriginal prompt
This pull request was created from Copilot chat.