Problems.
Write the piece, drive the whole agent loop, or repair a repo by prompting a coding agent. Most are graded against a real model, because that is what you will ship against.
0 of 85 solved
Show me at , . 10 matches
- 08Build Your First RAG Pipelineagent loopagentL03medium
- 09Fix a Broken RAG SystemdebugpytorchL03hard
- 26Make the Model Admit It Doesn't Knowimplement · liveagent · liveL03hard
- 53Answer With Citations, or Say You Can'timplement · liveagent · liveL03medium
- 74Check Every Sentence Has a Sourceimplement · liveagent · liveL03medium
- 77Answer the Question That Needs Two Documentsimplement · liveagent · liveL03hard
- 78Hand Retrieval to the Model as a Toolimplement · liveagent · liveL03medium
- 79Decide When Two Documents Disagreeimplement · liveagent · liveL03medium
- 80Know When Not to Retrieveimplement · liveagent · liveL03medium
- 81Answer From a Repo That Does Not Fitimplement · liveagent · liveL03hard
10 of 85 problems