DEV Community

#agents

Posts

👋 Sign in for the ability to sort posts by relevant, latest, or top.
Designing MCP Tools for a 7B Model, Not a 70B One

Designing MCP Tools for a 7B Model, Not a 70B One

2
Comments 2
5 min read
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.

12
Comments 4
5 min read
When a Failed Agent Step Looks Finished

When a Failed Agent Step Looks Finished

Comments
5 min read
Team Memory Hubs for AI Agents: What TencentDB-Agent-Memory Solves — and What It Misses

Team Memory Hubs for AI Agents: What TencentDB-Agent-Memory Solves — and What It Misses

Comments
6 min read
How Do You Build an Evaluation Harness for AI Agents?

How Do You Build an Evaluation Harness for AI Agents?

2
Comments 1
3 min read
Fast Agent Quality Gates: Deterministic Rules Over LLM Judges

Fast Agent Quality Gates: Deterministic Rules Over LLM Judges

2
Comments 2
6 min read
Is Learning Syntax Still Worth It in the Age of AI?

Is Learning Syntax Still Worth It in the Age of AI?

Comments
5 min read
Why Your Agent Token Is Your Agent's Identity: Building Credential Infrastructure for Autonomous Workforces

Why Your Agent Token Is Your Agent's Identity: Building Credential Infrastructure for Autonomous Workforces

Comments
6 min read
🛫 I Vibe Coded a Website at 35,000 Feet 🛬

🛫 I Vibe Coded a Website at 35,000 Feet 🛬

6
Comments
3 min read
🚀 Build an End-to-End AI Video Production Pipeline with Hermes Agent and Remotion

Hermes Agent Challenge Submission: Write About Hermes Agent

🚀 Build an End-to-End AI Video Production Pipeline with Hermes Agent and Remotion

6
Comments 1
3 min read
I made my website callable by another AI agent — here's the actual JSON-RPC

I made my website callable by another AI agent — here's the actual JSON-RPC

Comments
3 min read
What If Agent Tasks Were Installable Packages?

What If Agent Tasks Were Installable Packages?

Comments
6 min read
I measured how much my coding agent actually knows about my stack. It was 40%.

I measured how much my coding agent actually knows about my stack. It was 40%.

1
Comments
3 min read
Your LLM sends valid data in an invalid shape

Your LLM sends valid data in an invalid shape

1
Comments 1
6 min read
I built a BYOK AI agent that tests your app while you're building it, then turns the passing run into a real Playwright spec

I built a BYOK AI agent that tests your app while you're building it, then turns the passing run into a real Playwright spec

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