Intro to AgentKit - Create a RAG Agent

Build and deploy an OpenAI AgentKit workflow end-to-end: design a production-ready RAG agent in AgentBuilder with guardrails and the built-in File Search (Anna Karenina), preview with evals and tracing, and embed the workflow in a customizable ChatKit UI for your web app. --- Connect with me 🤗 - X: https://x.com/_alejandroao - LinkedIn: https://www.linkedin.com/in/alejandro-ao/ --- 🔗 Links - 🚀 Complete AI Engineer Bootcamp: https://learn.alejandro-ao.com/ - ❤️ Support me: https://link.alejandro-ao.com/l83gNq - 💬 Join the Discord Help Server: https://link.alejandro-ao.com/HrFKZn - ✉️ Get channel + AI Engineering updates: https://link.alejandro-ao.com/AIIguB --- 🤓 Topics Covered - OpenAI AgentKit overview: AgentBuilder + ChatKit - Designing agentic workflows with nodes: start/end, pass/fail routing, chaining agents - Input variables and shared context across nodes - Guardrails configuration: jailbreak detection, PII, moderation, hallucination, continue-on-error - Building a RAG agent: system prompt, chat history, tool-calling loop vs simple LLM call --- ⏰ *Timestamps* 0:00:00 - Intro 0:00:56 - Announcement 0:03:21 - Opening AgentBuilder 0:04:10 - Building a RAG agent with AgentKit 0:12:58 - ChatKit integration