DEV Community

#llmops

Posts

đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.
Your guardrail regex didn't protect your agent. It froze your entire Python event loop.

Your guardrail regex didn't protect your agent. It froze your entire Python event loop.

1
Comments 1
5 min read
You ship agent to production & 3 days later internal user says it's not answering well - next move?

You ship agent to production & 3 days later internal user says it's not answering well - next move?

Comments 1
2 min read
The stream died halfway through. Your proxy treated it as a clean stop.

The stream died halfway through. Your proxy treated it as a clean stop.

Comments
3 min read
Day 26 — Why Your AI Agent Might Be Slow Even When Every Tool Is Fast

Day 26 — Why Your AI Agent Might Be Slow Even When Every Tool Is Fast

1
Comments 3
5 min read
When Autonomous Agents Target the Weakest Link: Architectural Risks and Defensive Engineering

When Autonomous Agents Target the Weakest Link: Architectural Risks and Defensive Engineering

Comments
10 min read
Sonnet 5.5 vs Sonnet 5: When To Reach For Which

Sonnet 5.5 vs Sonnet 5: When To Reach For Which

Comments
4 min read
You fine-tuned at full precision. You serve in FP8. Those were two different models.

You fine-tuned at full precision. You serve in FP8. Those were two different models.

Comments
3 min read
A point release halved your KV cache memory. You did not choose that trade.

A point release halved your KV cache memory. You did not choose that trade.

1
Comments 2
4 min read
LLMOps: Shipping AI to Production

LLMOps: Shipping AI to Production

Comments
12 min read
Production Architecture for Agentic AI: State, Guardrails, and Fallbacks

Production Architecture for Agentic AI: State, Guardrails, and Fallbacks

Comments
4 min read
Stable Image Core vs Stable Image Ultra: When To Reach For Which

Stable Image Core vs Stable Image Ultra: When To Reach For Which

Comments
3 min read
Human vs. automated evals: who should judge your AI agent?

Human vs. automated evals: who should judge your AI agent?

Comments
6 min read
How I Built AI-Native Products as a One-Person Software Factory

How I Built AI-Native Products as a One-Person Software Factory

20
Comments 7
10 min read
I Gave an AI Agent Three Years of Deal History. Here's the First Pattern It Found.

I Gave an AI Agent Three Years of Deal History. Here's the First Pattern It Found.

Comments 1
3 min read
Running LLM-as-a-judge on live traffic without blowing your budget

Running LLM-as-a-judge on live traffic without blowing your budget

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