DEV Community

#llm

Posts

đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.
How to Implement Prompt Caching on Amazon Bedrock and Cut Inference Costs in Half

How to Implement Prompt Caching on Amazon Bedrock and Cut Inference Costs in Half

Comments
12 min read
Per-customer LLM cost attribution for multi-step agents (LangGraph, CrewAI)

Per-customer LLM cost attribution for multi-step agents (LangGraph, CrewAI)

Comments 1
2 min read
Securing AI-Powered Applications: A Comprehensive Guide to Protecting Your LLM-Integrated Web App

Securing AI-Powered Applications: A Comprehensive Guide to Protecting Your LLM-Integrated Web App

Comments
8 min read
AI Agent API Costs: How ClawRouter Cuts LLM Spending by 500x

AI Agent API Costs: How ClawRouter Cuts LLM Spending by 500x

Comments
8 min read
How I ran LLM + RAG fully offline on Android using MNN

How I ran LLM + RAG fully offline on Android using MNN

Comments
3 min read
5 Agent Design Patterns Every Developer Needs to Know in 2026

5 Agent Design Patterns Every Developer Needs to Know in 2026

2
Comments 1
15 min read
Hermes Agent: Honest Review

Hermes Agent: Honest Review

6
Comments 1
4 min read
Giving Your AI the Right Context with Model Context Protocol (MCP)

Giving Your AI the Right Context with Model Context Protocol (MCP)

3
Comments
4 min read
Your AI agent is wasting 90% of its tokens on field names"

Your AI agent is wasting 90% of its tokens on field names"

Comments
7 min read
Fundamental matters more in AI era

Fundamental matters more in AI era

Comments
3 min read
Dash It All! Is AI Em Dash Addiction Real?

Dash It All! Is AI Em Dash Addiction Real?

9
Comments 1
6 min read
How to Run MCP Servers in Production (Security, Scaling & Governance for AI Tooling)

How to Run MCP Servers in Production (Security, Scaling & Governance for AI Tooling)

72
Comments 14
8 min read
Agentic Coding: Rules, skills, subagents, and reflection—how we steer models so multi-step work stays coherent.

Agentic Coding: Rules, skills, subagents, and reflection—how we steer models so multi-step work stays coherent.

8
Comments 2
4 min read
The "State Export" Hack: Rescuing Overloaded LLM Chats

The "State Export" Hack: Rescuing Overloaded LLM Chats

3
Comments
2 min read
12 Things Nobody Tells You About Building a Production RAG System

12 Things Nobody Tells You About Building a Production RAG System

3
Comments 1
9 min read
đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.