From LangChain to LangSmith and LangGraph: the Future of AI
summary
Shows how LangChain, LangSmith and LangGraph are wired together to build a real agent that searches Moroccan news: chains prompt parsing into multiple Google-search API calls, filters only .ma sites, scrapes articles, builds a dataset of titles and summaries and returns structured results, with the exact code shared. Explains LangChain as orchestration, demonstrates LangSmith for tracing and quality checks (logs, token usage, dataset comparisons) and LangGraph for visual, scalable agent flows.
AI-written summary · about
chapters (11)
- 0:00Introduction to AI tools
- 1:05What is LangChain
- 3:32Limitations of LangChain
- 5:20Introducing LangSmith
- 8:12LangSmith features and benefits
- 11:26Why use LangGraph
- 13:14LangGraph explained
- 15:02LangChain vs LangGraph
- 15:31Demo introduction
- 17:41Live coding demo
- 21:31Resources and conclusion
related talks
01h 59mBuilding Agentic and Multi-Agent Systems with LangGraph
28mAI Agents Graph: Your Following Tool in Your Java AI Journey
01h 50mChatGPT & LLMs: A Practical Starter's Guide to Language Chains
01h 59mLLM applications with LangChain
25mLangChain with Azure AI: Building LLM powered Applications
01h 34mA Practical Starter's Guide to building LLM based projects
29mBuilding Modular AI Agents with LangGraph, MCP, and
24mChaining, Smithing, and Graphing LLMs on Google Cloud