| FazBrowse GitHub Viewer | Trending | | Home |
| Tools: [Download Repo ZIP] [Original HTTPS Page] |
…task_status/task_stop/task_file_info/prompt_examples)
Foundation for autonomous prompt optimization (#94) and A/B testing promotion (#59). Scores pipeline task outputs against a 5-dimension rubric (Specificity, Actionability, Completeness, Internal Consistency, Conciseness) using structured LLM output. Includes CLI helper for scoring tasks from completed run directories. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
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>
| Back | FazBrowse Home | New Git URL |
Replaces fabricated tool names (plan_create, planexe.create_plan, etc.) with the real MCP tools from mcp_cloud/app.py:
Includes corrected parameter names, workflow steps, and example code.
Apologies to Simon for the hallucinations — this was a serious error.