Repository navigation
Elicit completeness gate - #76
Merged
Merged
Conversation
Two gauntlet-validated additions to the V3 elicit skill. Output-shape: elicit the result shape field-by-field and give any derived or disclosed figure the core-method treatment. Fixes the result-shape decision shipped elicit repeatedly dropped or scoped out. Completeness gate: before finishing, walk the decision-class checklist and keep asking until every relevant class is answered or ruled out of scope. Forces the surfacing pass rather than concluding when the main flow first coheres. Both sections domain-neutral. Bespoke non-inferable capture 50-67%->89% across three held-out tasks (loan-schedule 100%), roughly 2x the nearest competitor, under real-agent execution with the allium check hook live.
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Two gauntlet-validated additions to the elicit skill.