DEV Community

#llmops

Posts

đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.
Production RAG Architecture: LLMOps Patterns & Checklist

Production RAG Architecture: LLMOps Patterns & Checklist

1
Comments
4 min read
LLMOps for RAG Systems — Production Checklist

LLMOps for RAG Systems — Production Checklist

1
Comments
4 min read
Mem0 vs Zep vs LangChain Memory vs Letta: Which One Actually Remembers?

Mem0 vs Zep vs LangChain Memory vs Letta: Which One Actually Remembers?

1
Comments 2
4 min read
Stop Guessing Which Model Is Better: Amazon Bedrock Model Evaluation Hands-On

Stop Guessing Which Model Is Better: Amazon Bedrock Model Evaluation Hands-On

Comments
5 min read
LLMOps for Compound AI Systems — Observability & Cost

LLMOps for Compound AI Systems — Observability & Cost

1
Comments
4 min read
Don't Fine-Tune. Unless You Can Answer These Three Questions.

Don't Fine-Tune. Unless You Can Answer These Three Questions.

1
Comments 1
4 min read
The throttle that wasn't a cap: rate vs sum in agent budgets

The throttle that wasn't a cap: rate vs sum in agent budgets

Comments
5 min read
Invoked, not executed

Invoked, not executed

Comments
5 min read
Give Your Mem0 Agent Session-Scoped Memory in 15 Minutes (One Filter You're Probably Skipping)

Give Your Mem0 Agent Session-Scoped Memory in 15 Minutes (One Filter You're Probably Skipping)

7
Comments 8
4 min read
LLMOps for Production RAG: Observability & Cost Guide

LLMOps for Production RAG: Observability & Cost Guide

2
Comments 1
4 min read
Switchboard: building a tool router so your AI agent stops drowning in MCP tools

Switchboard: building a tool router so your AI agent stops drowning in MCP tools

Comments
13 min read
Your AI Agent Doesn't Need a Bigger Context Window. It Needs an Eviction Policy.

Compares messy agent logs to unedited diaries

Your AI Agent Doesn't Need a Bigger Context Window. It Needs an Eviction Policy.

4
Comments 10
5 min read
Detailed instructions written for an earlier generation of AI models become harmful on today's models

Detailed instructions written for an earlier generation of AI models become harmful on today's models

Comments
7 min read
We caught our AI agent building backdoors to run itself more

We caught our AI agent building backdoors to run itself more

1
Comments 2
6 min read
The Dedicated-GPU Trap: Why "Frontier, Per-Token" Wins Until You Have a Dozen Clients

The Dedicated-GPU Trap: Why "Frontier, Per-Token" Wins Until You Have a Dozen Clients

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