-
[Duo Workflow]: compare actual patch with expected using LangSmith uuid 0 of 2 checklist items completed
- Merged
- 1
updated -
Implement a CLI command to evaluate Duo Workflow fix-broken-pipeline with LLM judge 0 of 2 checklist items completed
- Merged
- 5
- Approved
updated -
Support dataset upsert logic 0 of 2 checklist items completed
- Merged
- 2
- Approved
updated -
Upload the dataset "workflow fix broken pipeline stubs" using CLI 0 of 2 checklist items completed
- Merged
- 8
- Approved
updated -
Update docs to clarify when to use Langsmith UI 0 of 2 checklist items completed
- Merged
- Approved
updated -
docs: update the readme with a quickstart guide 0 of 2 checklist items completed
- Merged
- 14
- Approved
updated -
Update file chat_evaluation.md spelling 0 of 2 checklist items completed
- Merged
- 2
- Approved
updated -
Experiment: Implement the first version of Agent Factory for Duo Workflow 1 of 2 checklist items completed
-
Add gcloud to tool-info 0 of 2 checklist items completed
- Merged
- 2
- Approved
updated -
Update documentation around running evaluations locally 0 of 2 checklist items completed
- Merged
- 15
- Approved
updated -
Move the Duo Chat evaluation scripts to the `eli5` package 0 of 2 checklist items completed
- Merged
- 13
- Approved
updated -
Add more comprehensive dataset descriptions 0 of 2 checklist items completed
- Merged
- 10
updated -
- Merged
- 7
- Approved
updated -
Update documentation with information about datasets 0 of 2 checklist items completed
- Merged
- 6
- Approved
updated -
- Merged
- Approved
updated -
Support for CSV and JSONL files with string values for `inputs` and `outputs` keys 1 of 2 checklist items completed
- Merged
- Approved
updated -
- Merged
- Approved
updated