Skip to content

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 , . 85 matches

  1. 31Write a Ralph Loop From Scratchimplement · liveagent · liveL05medium
  2. 32Repair: word_count says every sentence is one wordrepair sessionstdlibL05medium
  3. 33Repair: totals are wrong for amounts over $999repair sessionstdlibL05medium
  4. 34Repair: article URLs are full of dashesrepair sessionstdlibL05medium
  5. 35Stay Under the Token BudgetoptimizeagentL01medium
  6. 36Parse JSON From a StreamimplementstdlibL01medium
  7. 37Rerank the Retrieved Chunksimplement · liveagent · liveL02medium
  8. 38Batch Calls Without Tripping the Rate LimitimplementagentL01medium
  9. 39Trim the Conversation, Keep the System PromptimplementagentL01medium
  10. 40Build BM25 From ScratchimplementstdlibL02medium
  11. 41Catch the Regression Between Two VersionsimplementstdlibL07medium
  12. 42Hand Off to a Specialist Agentimplement · liveagent · liveL05medium
  13. 43Write the Tests That Catch the Bugwrite testsstdlibL07medium
  14. 44Remember What Mattersimplement · liveagent · liveL05medium
  15. 45Find the First Turn That Went WrongimplementagentL07medium
85 problems, showing 31 to 45