DEV Community

Artificial Intelligence

Artificial intelligence leverages computers and machines to mimic the problem-solving and decision-making capabilities found in humans and in nature.

Posts

👋 Sign in for the ability to sort posts by relevant, latest, or top.
What If Your AI Agent Never Had to Leave the Browser? (Demo 🚀)

Insights from speaking at AGNTCon Europe

What If Your AI Agent Never Had to Leave the Browser? (Demo 🚀)

81
Picked as gem Comments 59
8 min read
Two Weeks In: A 15-Year QA Veteran, Back to Being the New Guy

Relatable impostor syndrome at an AI startup

Two Weeks In: A 15-Year QA Veteran, Back to Being the New Guy

64
Comments 50
6 min read
Cheap RAG in Go with Gemini File Search: no vector DB, two calls, one hosted store

Cheap RAG in Go with Gemini File Search: no vector DB, two calls, one hosted store

25
Comments 2
14 min read
The Curiosity Gap: Why We've Stopped Asking Questions

The Curiosity Gap: Why We've Stopped Asking Questions

10
Comments 1
4 min read
We Solved the How to Code Problem. We Still Haven't Solved "What to Build."

We Solved the How to Code Problem. We Still Haven't Solved "What to Build."

16
Comments 6
5 min read
I interviewed the people who rejected me. Here's what their hiring process is actually optimizing for.

I interviewed the people who rejected me. Here's what their hiring process is actually optimizing for.

14
Comments
6 min read
Where Trust in Automated Review Actually Comes From

Where Trust in Automated Review Actually Comes From

2
Comments 1
4 min read
How do you stop an LLM from leaking API keys in the code it writes? Default to secret

How do you stop an LLM from leaking API keys in the code it writes? Default to secret

6
Comments 4
8 min read
I Told a PR Nothing Would Break. Qodo Checked.

I Told a PR Nothing Would Break. Qodo Checked.

5
Comments
4 min read
RAG ranking is not the same as judging with Jev

RAG ranking is not the same as judging with Jev

1
Comments
9 min read
I Cut 2,490 Agent Test Runs to 206 and Kept the Same Coverage

I Cut 2,490 Agent Test Runs to 206 and Kept the Same Coverage

7
Comments 1
5 min read
Your AI eval is green because it never called the model

Your AI eval is green because it never called the model

Comments 4
6 min read
I built a self-hostable AI data analyst — 4 agents, sandboxed code execution, your choice of LLM

I built a self-hostable AI data analyst — 4 agents, sandboxed code execution, your choice of LLM

1
Comments 1
5 min read
My most important test had never failed — because what it proved was 1 = 1

My most important test had never failed — because what it proved was 1 = 1

Comments
6 min read
Claude Code now supports AGENTS.md Natively - Here's how it actually works

Claude Code now supports AGENTS.md Natively - Here's how it actually works

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