Articles for people who
ship the stack
Original rewrites on React, Node.js, TypeScript and AI — practical notes from the same engineering practice behind our operator software. Article bodies are in English.
Tagged: llamaindex
AI agent frameworks compared: LangChain, LangGraph, CrewAI, and more
Pick orchestration by control-flow needs—chains, graphs, crews, chat agents, or data agents—without stacking every framework into one unmaintainable service.
889 wordsRead articleLangGraph research agent with LlamaIndex retrieval and HITL coding
Format-aware chunking, structured intent routing, parallel specialist retrievers, and interrupt-gated CLI coding turn papers into executable experiments safely.
839 wordsRead articlePick RAG Frameworks by Workload, Not by LangChain Momentum
When search and PDF-QA are not agents, Haystack and LlamaIndex can beat a LangChain monolith on latency, deps, and debuggability.
1200 wordsRead articleBuild a Wikipedia RAG chat assistant with LlamaIndex and ReAct
Index Wikipedia pages on demand, embed chunks with a small encoder, and let a ReAct agent call a query-engine tool so Chainlit answers stay grounded in retrieved evidence.
1314 wordsRead articleFrom "Go Ahead" to Done: State, Approval and Idempotency for Acting Agents
Learn how explicit proposals, bound approvals, revalidation, idempotency keys and outcome verification turn a multi-agent refund workflow into one you can trust.
3113 wordsRead articleLangChain vs LlamaIndex: Choosing the Right LLM Framework
A comparison of LangChain and LlamaIndex covering architecture, RAG, agents, and performance to help you pick the right framework for your AI project.
1706 wordsRead article
About these articles
Request a 24h estimate
Need the same stack in a production operator layer? Send the brief — estimate within 24 hours.