DEV Community

#agents

Posts

đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.
Human in the loop: designing approvals people do not skip

Human in the loop: designing approvals people do not skip

Comments 1
4 min read
Everyone Is Building Personal AI for Everyone. I'm Building Mine for One Person.

Everyone Is Building Personal AI for Everyone. I'm Building Mine for One Person.

Comments
3 min read
I built a system that attacks its own AI agents every night. Here's what it found — including in Google's own code.

I built a system that attacks its own AI agents every night. Here's what it found — including in Google's own code.

Comments 1
4 min read
Context Engineering Needs a Build System, Not a Prompt Folder

Context Engineering Needs a Build System, Not a Prompt Folder

1
Comments
5 min read
AI Agents Don't Need More Intelligence. They Need Better Architecture.

AI Agents Don't Need More Intelligence. They Need Better Architecture.

2
Comments
17 min read
Human, agents, code, judge: adding Jev without replacing peer review

Human, agents, code, judge: adding Jev without replacing peer review

1
Comments
5 min read
Hash Chains Protect Every Record Except the One That Matters

Hash Chains Protect Every Record Except the One That Matters

4
Comments
7 min read
Sentinel by Albertic: An Enterprise Agent Fleet for Environmental Intelligence

Sentinel by Albertic: An Enterprise Agent Fleet for Environmental Intelligence

Comments
3 min read
The agent host didn't have the lifecycle boundaries I assumed

The agent host didn't have the lifecycle boundaries I assumed

7
Comments 28
6 min read
What happens when enterprise requirements hit Strands, LangGraph, and CrewAI - 45 runs measured

Real-world benchmarks reveal hidden framework bugs

What happens when enterprise requirements hit Strands, LangGraph, and CrewAI - 45 runs measured

8
Picked as gem Comments 27
4 min read
Give your AI agent a budget before you give it a wallet

Give your AI agent a budget before you give it a wallet

Comments 3
2 min read
Secret Agent Overmind: diagnose an AI agent with code, traces, evals and datasets

Secret Agent Overmind: diagnose an AI agent with code, traces, evals and datasets

Comments
7 min read
The Path Matched, the Tree Did Not: A Myth-Busting FAQ

The Path Matched, the Tree Did Not: A Myth-Busting FAQ

Comments 1
8 min read
Evidence-Gated Agency: building an agent that can't be optimistic

Evidence-Gated Agency: building an agent that can't be optimistic

Comments
7 min read
A Healthy Service Does Not Mean the Task May Continue: An OpenHands Liveness Failure and Agent Recovery Boundaries

A Healthy Service Does Not Mean the Task May Continue: An OpenHands Liveness Failure and Agent Recovery Boundaries

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