DEV Community

#agents

Posts

đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.
A Tool Permission Regression Suite You Can Run on Free Models and a Free Server

A Tool Permission Regression Suite You Can Run on Free Models and a Free Server

Comments
5 min read
A New Model Drop Is a Diff, Not an Upgrade: Tool-Call Boundary Checks

A New Model Drop Is a Diff, Not an Upgrade: Tool-Call Boundary Checks

Comments
3 min read
Who Gets to Say the Agent Behaved Correctly?

Who Gets to Say the Agent Behaved Correctly?

4
Comments
5 min read
loveyourclanker.org

loveyourclanker.org

Comments
1 min read
Turbocharge Coding Agents with Your Test Coverage

Turbocharge Coding Agents with Your Test Coverage

5
Comments 2
4 min read
When Skill Evolution Means Removing Instructions

Why prompt instructions decay over time

When Skill Evolution Means Removing Instructions

11
Comments 19
5 min read
I filled my agent's wiki with contradictions. It never gave a wrong answer.

I filled my agent's wiki with contradictions. It never gave a wrong answer.

Comments 1
5 min read
The settlement is the write event

The settlement is the write event

Comments 1
6 min read
Context Windows Are Not Memory

Context Windows Are Not Memory

1
Comments
1 min read
For Structured Data, Retrieval Accuracy Isn't a Model Problem

For Structured Data, Retrieval Accuracy Isn't a Model Problem

Comments 2
3 min read
AI Agents Don’t Need More Context. They Need Memory.

AI Agents Don’t Need More Context. They Need Memory.

2
Comments 2
4 min read
Unit Economics Over Growth: What Investors Actually Want from SaaS in the Agentic Era

Unit Economics Over Growth: What Investors Actually Want from SaaS in the Agentic Era

1
Comments 1
10 min read
Delegating to AI Means Governing the Environment

Delegating to AI Means Governing the Environment

Comments
12 min read
I Edited the Task Mid-Flight. The Agent Stopped Instead of Guessing.

I Edited the Task Mid-Flight. The Agent Stopped Instead of Guessing.

2
Comments 1
12 min read
A Free Replay Bench for Agent Tool-Call Failures Before You Deploy

A Free Replay Bench for Agent Tool-Call Failures Before You Deploy

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