Tag feed

#langchain

840 posts146 followers

Explore Hashnode

Alternatives

Trending tags this week

AAAditya Agrawaladityagrawal45.hashnode.dev7h ago · 13 min read

Myth: RAG Makes LLMs Accurate. Fact: It Depends.

The hook Three weeks after we shipped our RAG-based supplier support chatbot, a supplier asked it a straightforward question about payment terms. The bot answered confidently. The answer was wrong. No

1

K

AAkashakashbuilds.hashnode.dev6h ago · 8 min read

Building an AI Coding Assistant: From Concept to Code Generation

Building an AI Coding Assistant: From Concept to Code Generation If you've ever wished you could tell an AI to build an app and have it actually write the entire project file by file, this blog post i

0

SMShams Mukhtarshamsmukhtar.hashnode.dev1d ago · 13 min read

The LLM Is the Engine—LangChain, LangGraph, and LangSmith Are the Engineering Layer

Central thesis: LangChain, LangGraph, and LangSmith do not replace the large language model. They form an engineering layer around it. LangChain assembles the model, prompts, tools, retrieval, and con

0

AKAyush kumarayush6318.hashnode.dev2d ago · 10 min read

Turning Any YouTube Video Into a Personal Study Companion: Building the YouTube Study & Research Studio

Introduction YouTube has quietly become one of the biggest learning platforms in the world. Lectures, conference talks, tutorials, interviews — there's a video for almost everything. But it comes with

0

AHAntónio Hernándezagentbuildlog.hashnode.dev5d ago · 10 min read

Between Drawing the Graph and Hiding It: What LangChain's Middle Tier Costs

TL;DR: Porting Conductor to create_agent() deleted graph.py entirely (-328 lines) and replaced three hand-rolled loop controls with OOTB middleware. What didn't go away: the SetupStateMachine gate, no

0

Ddebbieshapirolabyrinthanalyticsconsulting.hashnode.devJul 25 · 6 min read

What a LangGraph Engagement Looks Like

When a data engineering team first hears "LangGraph implementation," the mental picture is often a black-box sprint that delivers a finished agent overnight. In reality the process is a series of focu

0

DSDarsh Shahfreecodecamp.orgJul 24 · 11 min read

How to Use Prompt Engineering and Context Engineering for AI Agents

In this tutorial, I’ll show you how prompt engineering and context engineering can improve an AI agent's performance. We’ll build a simple local agent, start with a baseline input, then improve it wit

0

PCprashant chouhangenerative-ai-with-javascript.hashnode.devJul 23 · 13 min read

Where RAG Fails: Understand the Limitations

GenAI with JS Retrieval-Augmented Generation (RAG) is a practical way to build AI applications that answer questions using your own documents. A RAG application can search PDFs, Markdown files, produc

1

A

STSujal Tangdesujaltangde.hashnode.devJul 22 · 13 min read

Tools, MCP, and Skills: What Each One Actually Does

The Sentence That Settles It Here is the line that does more work than everything else written about this comparison: Tools are what an agent can do. MCP is where those tools come from. Skills are ho

2

KC

RRelayShieldAdminrelayshield.hashnode.devJul 22 · 3 min read

From Advisory Tool to Mandatory Gate: A LangChain Reference Implementation

Our last post closed with an open question: a commenter had made the point that a Tool an agent may call isn't the same control as a gate the system must pass before a high-impact action, and we said

0

#langchain

Search Hashnode

#langchain

Explore Hashnode

Trending tags this week

Myth: RAG Makes LLMs Accurate. Fact: It Depends.

Building an AI Coding Assistant: From Concept to Code Generation

The LLM Is the Engine—LangChain, LangGraph, and LangSmith Are the Engineering Layer

Turning Any YouTube Video Into a Personal Study Companion: Building the YouTube Study & Research Studio

Between Drawing the Graph and Hiding It: What LangChain's Middle Tier Costs

What a LangGraph Engagement Looks Like

How to Use Prompt Engineering and Context Engineering for AI Agents

Where RAG Fails: Understand the Limitations

Tools, MCP, and Skills: What Each One Actually Does

From Advisory Tool to Mandatory Gate: A LangChain Reference Implementation