Add A/B experiment runner and results tracker (#94/#59)#227
Open
neoneye wants to merge 1 commit intofeature/94-task-output-scorerfrom
Open
Add A/B experiment runner and results tracker (#94/#59)#227neoneye wants to merge 1 commit intofeature/94-task-output-scorerfrom
neoneye wants to merge 1 commit intofeature/94-task-output-scorerfrom
Conversation
Minimal experiment infrastructure for prompt optimization (#94) and A/B testing promotion (#59). Runs baseline vs candidate system prompts on a task function, scores both outputs with the task output scorer, and logs results to a JSONL tracker. Includes experiment config, runner with task registry, results tracker, and CLI entry point. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
1 task
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary
scoring/experiment_config.py— configuration dataclass for A/B experimentsscoring/experiment_runner.py— runs baseline vs candidate system prompts on task functions, scores both, compares with configurable thresholdscoring/results_tracker.py— JSONL append-only results log with summary/filteringscoring/run_experiment.py— CLI entry point for running experimentsTest plan
ast.parse()all new files_compute_summary()correctly classifies keep/discard/inconclusiveResultsTrackerself-test passes (append, load, recent, summary)🤖 Generated with Claude Code