DEV Community

#agenticai

Posts

đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.
Wipro AI Frees 20,000 Employees' Capacity, No Layoffs

Wipro AI Frees 20,000 Employees' Capacity, No Layoffs

Comments
6 min read
Inside a Real Multi-Agent Claude Code Setup: Two Leads, 9 Projects, 40 Prompts a Day

Inside a Real Multi-Agent Claude Code Setup: Two Leads, 9 Projects, 40 Prompts a Day

Comments
13 min read
Your .NET Agent Is in Production, Your Engineering Discipline Isn’t.

Your .NET Agent Is in Production, Your Engineering Discipline Isn’t.

Comments
13 min read
SENTINEL-RL for SOCs: Architectural Gains and Cost Realities from Decoupling Semantic and Topological Reasoning

SENTINEL-RL for SOCs: Architectural Gains and Cost Realities from Decoupling Semantic and Topological Reasoning

Comments 1
5 min read
Graph as Architecture, Not Graph as Data: Why I Stopped Reaching for GraphRAG First

Graph as Architecture, Not Graph as Data: Why I Stopped Reaching for GraphRAG First

Comments
13 min read
I Got Claude Code to Talk to GPT, Grok, and a Local Ollama Model. Here’s What Actually Held Up

I Got Claude Code to Talk to GPT, Grok, and a Local Ollama Model. Here’s What Actually Held Up

Comments
8 min read
Meta's Muse Runs in a Sandbox Because Trust Is Broken

Meta's Muse Runs in a Sandbox Because Trust Is Broken

Comments 1
3 min read
Why LangGraph Wins: Benchmarking LangGraph, CrewAI, and AutoGen on 107 Real Data Engineering Tasks

Why LangGraph Wins: Benchmarking LangGraph, CrewAI, and AutoGen on 107 Real Data Engineering Tasks

Comments
5 min read
Claude Code Is an Operating Layer for Engineering Work: I Went Looking for Proof Instead of Just…

Claude Code Is an Operating Layer for Engineering Work: I Went Looking for Proof Instead of Just…

Comments
13 min read
How to Catch and Replay Production Agent Failures: Trace-Native CI/CD in Practice

How to Catch and Replay Production Agent Failures: Trace-Native CI/CD in Practice

Comments 1
4 min read
Clean Engineering, Unstable Measurement: A Preregistered Reliability Failure of Black-Box LLM Observers on Shared Endpoints

Clean Engineering, Unstable Measurement: A Preregistered Reliability Failure of Black-Box LLM Observers on Shared Endpoints

Comments 3
4 min read
Agent Skills vs MCP: I Stopped Reading Hot Takes and Measured the Actual Context Cost