DEV Community

#agents

Posts

đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.
6 months solo on a multi-agent PR reviewer. 10.93 vs 3.80 blockers/PR (claude alone) on my benchmark — please test on real PRs and tell me where it's wrong

6 months solo on a multi-agent PR reviewer. 10.93 vs 3.80 blockers/PR (claude alone) on my benchmark — please test on real PRs and tell me where it's wrong

Comments 1
2 min read
SIFS (SIFS Is Fast Search) - local code search for coding agents

SIFS (SIFS Is Fast Search) - local code search for coding agents

Comments
2 min read
Madrigal's "Failures as Eval Suites" Pattern and How Flow Already Provides the Infrastructure

Madrigal's "Failures as Eval Suites" Pattern and How Flow Already Provides the Infrastructure

Comments
6 min read
Agent vs Multi-Agent Systems: A Practical Guide with LangGraph & LangChain

Agent vs Multi-Agent Systems: A Practical Guide with LangGraph & LangChain

1
Comments
3 min read
Why Your AI Agent Calls the Wrong API (And How to Fix It)

Why Your AI Agent Calls the Wrong API (And How to Fix It)

3
Comments
7 min read
Kimi WebBridge just gave AI agents hands inside your browser — and kept your data local

Kimi WebBridge just gave AI agents hands inside your browser — and kept your data local

6
Comments
3 min read
Building AI agents with Vercel AI SDK

Building AI agents with Vercel AI SDK

Comments
6 min read
Como Testar Agentes de IA que Chamam suas APIs Sem Perder Dados

Como Testar Agentes de IA que Chamam suas APIs Sem Perder Dados

Comments
15 min read
OpenClaw Device Pairing: Why Your Dashboard Says 1008 and How to Fix It Safely

OpenClaw Device Pairing: Why Your Dashboard Says 1008 and How to Fix It Safely

Comments
7 min read
Microsoft shipped Agent 365 last Friday with something most people skipped past.

Microsoft shipped Agent 365 last Friday with something most people skipped past.

Comments
2 min read
Coding Agent Frustrations

Coding Agent Frustrations

Comments
4 min read
I Tested Claude Opus 4, GPT-4.1, GPT-4o, Sonnet 4, and Gemini 2.5 Pro on 10 Adversarial Scenarios. They All Broke on the Same One.

I Tested Claude Opus 4, GPT-4.1, GPT-4o, Sonnet 4, and Gemini 2.5 Pro on 10 Adversarial Scenarios. They All Broke on the Same One.

2
Comments
11 min read
your AI coding agent keeps re-making the bug you already fixed. here's the fix.

your AI coding agent keeps re-making the bug you already fixed. here's the fix.

1
Comments
6 min read
Context Governance for Coding Agents

Context Governance for Coding Agents

1
Comments 2
25 min read
Everyone’s Building AI Agents. Here’s the One I Built for Myself

Everyone’s Building AI Agents. Here’s the One I Built for Myself

1
Comments 1
2 min read
đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.