DEV Community

#agents

Posts

👋 Sign in for the ability to sort posts by relevant, latest, or top.
I Keep a Log of Every Rule My AI Agent Broke. The Patterns Are Uncomfortable.

I Keep a Log of Every Rule My AI Agent Broke. The Patterns Are Uncomfortable.

18
Comments 5
5 min read
Your AI Agent's Memory Is Not Its Source of Truth: The Hidden Risk of Stale Context

Your AI Agent's Memory Is Not Its Source of Truth: The Hidden Risk of Stale Context

6
Comments 5
13 min read
I Let Three AI Agents Run an Incident. The Most Useful Thing They Did Was Refuse Me.

I Let Three AI Agents Run an Incident. The Most Useful Thing They Did Was Refuse Me.

5
Comments
16 min read
Writing your own Switch agents from scratch: six Python agents that take a startup idea to a launch decision

Writing your own Switch agents from scratch: six Python agents that take a startup idea to a launch decision

Comments
7 min read
413 files, 1 badge: I re-ran Anthropic's memory test

413 files, 1 badge: I re-ran Anthropic's memory test

Comments 1
6 min read
I asked Claude to describe how my AI company functions, and here is what it wrote

I asked Claude to describe how my AI company functions, and here is what it wrote

Comments
9 min read
A proposal is not a reservation: what we learned putting AI agents in a lab's booking chat

A proposal is not a reservation: what we learned putting AI agents in a lab's booking chat

Comments
6 min read
Trust Network - An Agent-to-Agent Communication Protocol built on top of Switch

Trust Network - An Agent-to-Agent Communication Protocol built on top of Switch

Comments
8 min read
A new benchmark conned every frontier AI agent it tested.

A new benchmark conned every frontier AI agent it tested.

Comments
4 min read
How osFoundry detects that Claude Code is waiting on a permission prompt

How osFoundry detects that Claude Code is waiting on a permission prompt

Comments
10 min read
I made my AI agent prove its work: building Proofbot with Switch

I made my AI agent prove its work: building Proofbot with Switch

Comments
8 min read
One word decides who can order my code agent (a Switch addressing experiment)

One word decides who can order my code agent (a Switch addressing experiment)

Comments
4 min read
Why our incident agent remembers bad fixes using Hindsight

Why our incident agent remembers bad fixes using Hindsight

Comments
8 min read
How a Silent Fallback Corrupted My Hindsight Experiment

How a Silent Fallback Corrupted My Hindsight Experiment

Comments
4 min read
An AI agent built a Godot game. Then it checked its work.

An AI agent built a Godot game. Then it checked its work.

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