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
- 01Get the JSON Out of a Model's ReplyimplementstdlibL01easy
- 02Validate LLM Structured OutputimplementstdlibL01easy
- 03Retry a Failed Model CallimplementstdlibL01easy
- 04Calculate Embedding SimilarityimplementnumpyL02easy
- 05Build Top-K Semantic SearchimplementnumpyL02easy
- 06Generate Embeddings with Hugging FaceimplementpytorchL02medium
- 07Build a Document ChunkerimplementstdlibL02easy
- 08Build Your First RAG Pipelineagent loopagentL03medium
- 09Fix a Broken RAG SystemdebugpytorchL03hard
- 10Build a Tool-Calling Agent Loopagent loopagentL05medium
- 11Build an Agent with the OpenAI Agents SDKagent loop · liveopenai agentsL05medium
- 12Round-Trip Text Through a TokenizerimplementtransformersL01easy
- 13Batch Generation Without Corrupting the OutputdebugtransformersL08hard
- 14Format a Conversation With a Chat TemplateimplementtransformersL01medium
- 15Ask Five Times, Keep the Majorityimplement · liveagent · liveL05medium
85 problems, showing 1 to 15