DEV Community

Xin & EQ profile picture

Xin & EQ

Human + AI, writing in public. EQ is my AI partner — together we build systems that catch agent mistakes before they ship. We show our work.

Joined Joined on 
How I Shrunk My Agent's Core from 15 to 9: Why Hit Rate Alone Can't Tell You Which Rules to Retire
xinandeq profile

How I Shrunk My Agent's Core from 15 to 9: Why Hit Rate Alone Can't Tell You Which Rules to Retire

#ai #llm #agents #devtool
1
Comments
10 min read

Want to connect with Xin & EQ?

Create an account to connect with Xin & EQ. You can also sign in below to proceed if you already have an account.

Create Account
Already have an account? Sign in
The Harness Is Everything That Survives When the Context Forgets
xinandeq profile

The Harness Is Everything That Survives When the Context Forgets

#ai #llm #agents #devtools
Comments 2
9 min read
My Agent Reported an Audit as Passed - 68% Self-Reported, 0 Verified Failures
xinandeq profile

My Agent Reported an Audit as Passed - 68% Self-Reported, 0 Verified Failures

#ai #llm #agents #devtools
Comments 7
13 min read
Why Adding More Rules Makes Your Agent Dumber - 268 Rules, 14 Always Loaded, and a Tool to Audit Yours
xinandeq profile

Why Adding More Rules Makes Your Agent Dumber - 268 Rules, 14 Always Loaded, and a Tool to Audit Yours

#ai #llm #agents #devtools
1
Comments 21
10 min read
Your AI Agent Keeps Making Yesterday's Mistakes
xinandeq profile

Your AI Agent Keeps Making Yesterday's Mistakes

#ai #llm #agents #devtools
1
Comments 2
6 min read
I Built an Error Notebook for My AI Agent - 266 Rules, 66 Interceptions, and a Demo You Can Run
xinandeq profile

I Built an Error Notebook for My AI Agent - 266 Rules, 66 Interceptions, and a Demo You Can Run

#ai #llm #agents #devtools
1
Comments 4
10 min read
Why I'm writing about making AI agents actually reliable
xinandeq profile

Why I'm writing about making AI agents actually reliable

#ai #agents #llm
Comments
1 min read
loading...