DEV Community

#agents

Posts

👋 Sign in for the ability to sort posts by relevant, latest, or top.
The Dirty Secret Behind AI Agents (Demo 🚀)

Built in 80 lines without heavy frameworks

The Dirty Secret Behind AI Agents (Demo 🚀)

103
Comments 98
7 min read
Two coding agents editing the same issue, no merge conflict. Here is how git refs make that work

Two coding agents editing the same issue, no merge conflict. Here is how git refs make that work

5
Comments 1
5 min read
Observability should be a `git diff`, not a weekend: instrumenting an AI app with one command using SigNoz

Observability should be a `git diff`, not a weekend: instrumenting an AI app with one command using SigNoz

Comments
6 min read
Rotating the Hostile Seat: A Six-Round Adversarial Design Review Before Hardening an Agent

Rotating the Hostile Seat: A Six-Round Adversarial Design Review Before Hardening an Agent

Comments
7 min read
DevGuard AI: A Self-Observing Multi-Agent Security Pipeline Built on SigNoz

DevGuard AI: A Self-Observing Multi-Agent Security Pipeline Built on SigNoz

Comments
4 min read
Evidence First, Answer Second: Building an Observable Industrial AI Agent with SigNoz

Evidence First, Answer Second: Building an Observable Industrial AI Agent with SigNoz

Comments
6 min read
I Let an Agent Take Over an Account With Every Permission Check Green

I Let an Agent Take Over an Account With Every Permission Check Green

5
Comments 2
4 min read
Right Tool, Wrong Arguments: The Agent Failure Your Evals Wave Through

Right Tool, Wrong Arguments: The Agent Failure Your Evals Wave Through

2
Comments
4 min read
AgentATC

AgentATC

Comments
4 min read
SigNoz-ForgeGuard

SigNoz-ForgeGuard

Comments
6 min read
I priced enrichment for an AI agent at scale. The data costs more than the inference.

I priced enrichment for an AI agent at scale. The data costs more than the inference.

Comments
8 min read
Our AI Agent Told a Customer It Processed a Refund. It Didn't.

Our AI Agent Told a Customer It Processed a Refund. It Didn't.

Comments
5 min read
From One-Shot LLM to Multi-Turn Agent: How I Rebuilt My Text-to-Diagram Tool

From One-Shot LLM to Multi-Turn Agent: How I Rebuilt My Text-to-Diagram Tool

1
Comments
6 min read
The Oversight Ladder: the five levels of AI coding autonomy

The Oversight Ladder: the five levels of AI coding autonomy

Comments
7 min read
I replicated the vision-only Pokémon run Anthropic showcased on the Fable 5 launch page — then I read its thinking chains

I replicated the vision-only Pokémon run Anthropic showcased on the Fable 5 launch page — then I read its thinking chains

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