[{"data":1,"prerenderedAt":84},["ShallowReactive",2],{"term-a\u002Fagent":3,"related-a\u002Fagent":61},{"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":55,"sitemap":56,"stem":59,"subcategory":6,"__hash__":60},"terms\u002Fterms\u002Fa\u002Fagent.md","Agent",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",{},"An AI agent is an LLM that doesn't just answer questions — it takes actions. It can browse the web, run code, read files, call APIs, and use tools to complete multi-step tasks autonomously. You give it a goal ('book me a flight') and it figures out all the steps. Agents are why vibecoding can feel like having an intern who never sleeps.",[11,20,22],{"id":21},"real-talk","Real Talk",[16,24,25],{},"In AI, an agent is a system that perceives its environment and takes actions to achieve goals. LLM-based agents use the model as a reasoning engine, augmented with tool use (code execution, web search, API calls, file access). They operate in planning and execution loops, optionally with memory. Frameworks include LangChain, AutoGen, and Claude's tool use API.",[11,27,29],{"id":28},"when-youll-hear-this","When You'll Hear This",[16,31,32],{},"\"The AI agent wrote the code and ran the tests autonomously.\" \u002F \"Multi-agent systems have agents that specialize in different tasks.\"",{"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","An AI agent is an LLM that doesn't just answer questions — it takes actions.","intermediate","md","a",{},true,"\u002Fterms\u002Fa\u002Fagent",[49,50,51,52,53,54],"Agentic","Multi-Agent","Tool Use","Function Calling","MCP","LLM",{"title":5,"description":41},{"changefreq":57,"priority":58},"weekly",0.7,"terms\u002Fa\u002Fagent","hhmxljbw0ouQrri54DpN3ylyp-4r7o9aKqtNFPRcQr8",[62,66,69,73,78,81],{"title":49,"path":63,"acronym":6,"category":40,"difficulty":64,"description":65},"\u002Fterms\u002Fa\u002Fagentic","beginner","Agentic describes an AI system that acts autonomously — making decisions, taking actions, using tools, and working toward a goal without constant human han...",{"title":52,"path":67,"acronym":6,"category":40,"difficulty":42,"description":68},"\u002Fterms\u002Ff\u002Ffunction-calling","Function Calling is the OpenAI term for what Anthropic calls Tool Use — teaching the AI to call your code functions.",{"title":54,"path":70,"acronym":71,"category":40,"difficulty":64,"description":72},"\u002Fterms\u002Fl\u002Fllm","Large Language Model","An LLM is a humongous AI that read basically the entire internet and learned to predict what words come next, really really well.",{"title":53,"path":74,"acronym":75,"category":76,"difficulty":42,"description":77},"\u002Fterms\u002Fm\u002Fmcp","Model Context Protocol","vibecoding","MCP is like USB for AI — a universal standard for connecting AI models to external tools and data.",{"title":50,"path":79,"acronym":6,"category":40,"difficulty":42,"description":80},"\u002Fterms\u002Fm\u002Fmulti-agent","Multi-agent means multiple AI agents working together, each handling a different task.",{"title":51,"path":82,"acronym":6,"category":40,"difficulty":42,"description":83},"\u002Fterms\u002Ft\u002Ftool-use","Tool use is when an AI can call external functions, APIs, or programs to do things it can't do alone.",1776518254277]