fix(slack-agent): nudge model to actually call tools on test/demo requests#32
Merged
fix(slack-agent): nudge model to actually call tools on test/demo requests#32
Conversation
…uests User asked the prod bot 'test all your tools and give me a report' in a channel; bot replied verbally without calling any tools (0 tools / 0 steps in the audit row). Reasonable interpretation by Sonnet — the prompt says be concise + prefer tool calls 'when you need information', which 'test' doesn't trigger. Adds an explicit guideline: if the user asks to test, demonstrate, verify, exercise, or show off the tools/capabilities, actually call the relevant tools and report what they returned. Don't just describe them. Caught from prod audit immediately after Phase 4 ship. Made-with: Cursor
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
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Caught from prod after Phase 4 ship — "test all your tools and give me a report" got 0 tool calls / 0 steps because Sonnet read it as a description request, not an exercise request. Single-line prompt addition telling it to actually run tools when the user asks to test/demo/verify capabilities.
Made with Cursor