Highlights
Improved conversational notebook rendering and markdown reliability, including safer handling of currency-style `$` text
Updated prompts and guidance so generated MLJAR AutoML examples use `report_structured()` in a notebook-friendly way
Refined AutoLab experiment prompting to improve metric interpretation consistency
Reduced unstable scoring behavior across AutoLab iterations and added additional chat UX robustness polish
Improved
- Improved conversational notebook rendering and markdown reliability, including safer handling of currency-style
$text in assistant answers. - Updated prompts and guidance around MLJAR AutoML usage so generated examples use
report_structured()in a notebook-friendly way. - Refined AutoLab experiment prompting to improve consistency around metric interpretation.
- Added additional UX and robustness polish across notebook chat flows to keep outputs cleaner and easier to trust.
Fixed
- Reduced unstable scoring behavior across AutoLab iterations by tightening prompt behavior around metric interpretation and response quality.