Blazing the AI Trail: Using LangGraph to Conquer the Oregon Trail
summary
Hands-on build of a working agent workflow that actually binds Python LangGraph tools, implements vector retrieval against a Redis vector store, and adds semantic caching plus allow/block list routing so the agent skips irrelevant queries. Structured outputs (Pydantic schemas) enforce multiple-choice and API-friendly responses. Starter repo, Python 3.11+, Docker, and an OpenAI API key are required; tests in the repo demonstrate freeform, retrieval, cache-hit, and router behaviors and show the system working end-to-end.
AI-written summary · about
chapters (10)
- 0:00Welcome
- 2:49AI agents and LangGraph
- 6:23Agent architecture
- 13:49Oregon Trail project setup
- 17:24Agent graph for first question
- 28:21Handling multiple choice
- 39:40Retrieval tools for context
- 54:28Semantic caching for costs
- 1:04:45Router to block queries
- 1:09:26Summary and Q&A
related talks
53mHands-on with AI agents: From scratch to LangGraph
01h 59mBuilding Agentic and Multi-Agent Systems with LangGraph
28mBuild an AI Research Agent
30mBuilding Robust, Secure LLM and Agentic AI Workflows
01h 34mA Practical Starter's Guide to building LLM based projects
30mTutorial: Building an Observable AI Agent With an Open Source Stack
02h 08mIntroduction to AI Agents
29mDemystifying AI Agents with Python Code