[{"data":1,"prerenderedAt":81},["ShallowReactive",2],{"term-l\u002Fllm-tracing":3,"related-l\u002Fllm-tracing":60},{"id":4,"title":5,"acronym":6,"body":7,"category":40,"description":41,"difficulty":42,"extension":43,"letter":44,"meta":45,"navigation":46,"path":47,"related":48,"seo":54,"sitemap":55,"stem":58,"subcategory":6,"__hash__":59},"terms\u002Fterms\u002Fl\u002Fllm-tracing.md","LLM Tracing",null,{"type":8,"value":9,"toc":33},"minimark",[10,15,19,23,26,30],[11,12,14],"h2",{"id":13},"eli5-the-vibe-check","ELI5 - The Vibe Check",[16,17,18],"p",{},"When a chatbot gives a weird answer, 'it's an LLM, who knows' is not a debugging strategy. LLM tracing records every step an AI request actually took: which prompt was sent, what got retrieved for RAG, which tools got called, how many tokens it cost, and what came back at each stage. It turns a black box into something you can actually inspect after the fact, like a flight recorder for your AI pipeline.",[11,20,22],{"id":21},"real-talk","Real Talk",[16,24,25],{},"LLM tracing captures a structured, timestamped record of every step in an LLM application's execution, including prompts, retrieved context, tool calls, intermediate outputs, token counts, and latency per span, typically visualized as a waterfall or tree. Tools like LangSmith, Langfuse, and Helicone build on standard distributed tracing concepts but add LLM-specific metadata (prompt versions, token cost, model used) needed to debug multi-step agent and RAG pipelines.",[11,27,29],{"id":28},"when-youll-hear-this","When You'll Hear This",[16,31,32],{},"\"Pull up the trace, I want to see exactly what got retrieved before the model hallucinated.\" \u002F \"LLM tracing showed the agent was calling the same tool three times in a loop.\"",{"title":34,"searchDepth":35,"depth":35,"links":36},"",2,[37,38,39],{"id":13,"depth":35,"text":14},{"id":21,"depth":35,"text":22},{"id":28,"depth":35,"text":29},"ai","When a chatbot gives a weird answer, 'it's an LLM, who knows' is not a debugging strategy.","intermediate","md","l",{},true,"\u002Fterms\u002Fl\u002Fllm-tracing",[49,50,51,52,53],"Observability","Distributed Tracing","Hallucination","RAG","AI Agent",{"title":5,"description":41},{"changefreq":56,"priority":57},"weekly",0.7,"terms\u002Fl\u002Fllm-tracing","tkjgT1G4SOpTRZF-dqQjaJrWSxvcekGqPDjYxFnsViM",[61,64,69,73,77],{"title":53,"path":62,"acronym":6,"category":40,"difficulty":42,"description":63},"\u002Fterms\u002Fa\u002Fai-agent","An AI Agent is an AI system that can think, plan, and act on its own to accomplish a goal.",{"title":50,"path":65,"acronym":6,"category":66,"difficulty":67,"description":68},"\u002Fterms\u002Fd\u002Fdistributed-tracing","backend","advanced","Distributed tracing is request tracing's big brother — it works across multiple services, servers, and even data centers.",{"title":51,"path":70,"acronym":6,"category":71,"difficulty":42,"description":72},"\u002Fterms\u002Fh\u002Fhallucination","vibecoding","When an AI confidently makes something up — like citing a library that doesn't exist or generating code that calls a function that was never written.",{"title":49,"path":74,"acronym":6,"category":75,"difficulty":42,"description":76},"\u002Fterms\u002Fo\u002Fobservability","cicd","Observability is the ability to understand what's happening inside your system from the outside, using three types of data: metrics (numbers), logs (events...",{"title":52,"path":78,"acronym":79,"category":40,"difficulty":42,"description":80},"\u002Fterms\u002Fr\u002Frag","Retrieval Augmented Generation","RAG is how you give an AI access to your private documents without retraining it.",1792528095538]