DEV Community

# llm

Posts

👋 Sign in for the ability to sort posts by relevant, latest, or top.
Error Recovery in AI Agents: Graceful Degradation and Retry Strategies

Error Recovery in AI Agents: Graceful Degradation and Retry Strategies

Comments
6 min read
Tool Use vs RAG: picking the right approach

Tool Use vs RAG: picking the right approach

Comments
4 min read
Beyond the Chatbot: Architecture for Production-Grade Agents (Context as a Service)

Beyond the Chatbot: Architecture for Production-Grade Agents (Context as a Service)

Comments
3 min read
Will MCP become a standard? A look at what's coming

Will MCP become a standard? A look at what's coming

Comments
3 min read
Where does MCP fit in your stack?

Where does MCP fit in your stack?

Comments
4 min read
Cómo Reducir Costes LLM un 80% Sin Sacrificar Calidad en Producción

Cómo Reducir Costes LLM un 80% Sin Sacrificar Calidad en Producción

Comments
4 min read
The Reflection pattern: AI that checks its own work

The Reflection pattern: AI that checks its own work

Comments
5 min read
Prompts are logic, not strings: Why I contributed to Convo-Lang

Prompts are logic, not strings: Why I contributed to Convo-Lang

Comments
3 min read
Complete Ollama Tutorial (2026) – LLMs via CLI, Cloud & Python

Complete Ollama Tutorial (2026) – LLMs via CLI, Cloud & Python

1
Comments 1
4 min read
Build a Slack bot that uses your local tools

Build a Slack bot that uses your local tools

Comments
4 min read
MCP vs Function Calling — What's the difference?

MCP vs Function Calling — What's the difference?

Comments
3 min read
Your documents, your machine: DIY RAG with MCP

Your documents, your machine: DIY RAG with MCP

Comments
6 min read
Build a smarter smart home with Claude and MCP

Build a smarter smart home with Claude and MCP

Comments
4 min read
MCP vs ReAct: Protocol vs Pattern

MCP vs ReAct: Protocol vs Pattern

Comments
5 min read
I Found an LLM Weakness. Fixing It Cut My Token Usage 50%.

I Found an LLM Weakness. Fixing It Cut My Token Usage 50%.

Comments
6 min read
Why Your AI Agent Says "Done" But Nothing Actually Happened

Why Your AI Agent Says "Done" But Nothing Actually Happened

Comments
3 min read
How to Use Claude Code with Qwen models for Free (Linux)

How to Use Claude Code with Qwen models for Free (Linux)

Comments
2 min read
Demystifying ReAct: Why Reasoning and Acting is the Standard for LLM Agents

Demystifying ReAct: Why Reasoning and Acting is the Standard for LLM Agents

Comments
6 min read
Anthropic: From Pandemic-Era Safety Concerns to a $350B AI Company

Anthropic: From Pandemic-Era Safety Concerns to a $350B AI Company

Comments
5 min read
Loaders, Splitters & Embeddings — How Bad Chunking Breaks Even Perfect RAG Systems

Loaders, Splitters & Embeddings — How Bad Chunking Breaks Even Perfect RAG Systems

Comments
3 min read
RAG 2.0: Why Reranking Has Become the Core of Modern RAG Systems

RAG 2.0: Why Reranking Has Become the Core of Modern RAG Systems

Comments
4 min read
Amazon Bedrock: The AI Foundation That’s Powering NatWest Bank’s Digital Transformation

Amazon Bedrock: The AI Foundation That’s Powering NatWest Bank’s Digital Transformation

Comments
5 min read
Ejecuta Qwen3 + Ollama + Open WebUI en Docker: Tu propio AI Chat local 🧠

Ejecuta Qwen3 + Ollama + Open WebUI en Docker: Tu propio AI Chat local 🧠

Comments
2 min read
Understanding Large Language Models: A Developer's Guide

Understanding Large Language Models: A Developer's Guide

4
Comments
22 min read
Beyond Code Generation: LLMs for Code Understanding

Beyond Code Generation: LLMs for Code Understanding

Comments
12 min read
loading...