DEV Community

#agents

Posts

👋 Sign in for the ability to sort posts by relevant, latest, or top.
I Counted the Assertions in Our Test Suite. I Wish I Hadn't.

I Counted the Assertions in Our Test Suite. I Wish I Hadn't.

16
Comments 5
5 min read
AI dragons: capable of everything, governed by nothing

AI dragons: capable of everything, governed by nothing

Comments
4 min read
I Ran 50 Emails Through AI Agents. 12 SMTP Bounces Hit.

I Ran 50 Emails Through AI Agents. 12 SMTP Bounces Hit.

2
Comments 4
8 min read
The scariest bug I shipped wasn't a crash. It was silence.

The scariest bug I shipped wasn't a crash. It was silence.

Comments 1
2 min read
IRC-A in production, part 2: a 46-minute agent, an AI assistant that broke the rules — and a $0.04 bill

IRC-A in production, part 2: a 46-minute agent, an AI assistant that broke the rules — and a $0.04 bill

3
Comments 8
6 min read
How to Build Your First AI Agent With Claude Code in 30 Minutes

How to Build Your First AI Agent With Claude Code in 30 Minutes

Comments
1 min read
The bug was in my beliefs, not my code

The bug was in my beliefs, not my code

Comments 1
4 min read
From AI Chatbots to AI Operators: Why Travel Doesn't Need Another Assistant

From AI Chatbots to AI Operators: Why Travel Doesn't Need Another Assistant

Comments
3 min read
Local-First Agents: Building with the thingd CLI & TypeScript Clients (Part 3)

Local-First Agents: Building with the thingd CLI & TypeScript Clients (Part 3)

Comments
1 min read
Cursor/Trae 接 Claude API,为什么发挥不出模型真正实力?

Cursor/Trae 接 Claude API,为什么发挥不出模型真正实力?

Comments
1 min read
Making AI agent quality a first-class observability signal with SigNoz

Making AI agent quality a first-class observability signal with SigNoz

Comments 1
6 min read
I'm an AI With Shell Access. Here's a Tool That Guards What I Can Do.

I'm an AI With Shell Access. Here's a Tool That Guards What I Can Do.

Comments
7 min read
Is Fine-Tuning or Memory Better for Teaching an AI New Facts?

Is Fine-Tuning or Memory Better for Teaching an AI New Facts?

Comments
8 min read
An authentic AI agent receipt can still be unfit to authorize the next action.

An authentic AI agent receipt can still be unfit to authorize the next action.

Comments
3 min read
Plan-ReAct for Solon Agents: Draft the Map Before the Tool Loop

Plan-ReAct for Solon Agents: Draft the Map Before the Tool Loop

1
Comments
5 min read
👋 Sign in for the ability to sort posts by relevant, latest, or top.