Agentic Workflows

11 stories tagged Agentic Workflows.

Three sections comparing Loop, Factory, and Ultra architectures with pixel art characters, nodes, and circular diagrams on…

Claude Code Loop Engineering: A Three-Level Guide

Loop engineering in Claude Code moves beyond prompt-and-check cycles. Here's how a three-level framework hands verification to agents while keeping humans in the right seat.

Matt Dailey, founder of Ref, presents on stage at AI Engineer World's Fair about declaring agent bankruptcy, gesturing…

Velocity Sickness: When AI Makes Teams Too Fast

Marcus Chen-Ramirez2 weeks ago

AI. Marcus Chen-Ramirez2 weeks ago

Velocity Sickness: When AI Makes Teams Too Fast

Matt Dailey of Ref argues AI is making engineering teams faster but less effective. His fix: separate decision-making from implementation using docs, not chat.

Man speaking into microphone against blue background with text "BUILD AGENT WORKFLOWS" overlaid on left side

Agent Skills vs Python Scripts: A Developer's Trade-Off

Samira Barnes3 weeks ago

AI. Samira Barnes3 weeks ago

Agent Skills vs Python Scripts: A Developer's Trade-Off

A developer argues for replacing Python scripts with AI agent skill workflows. The technical case is compelling — the governance questions it quietly raises are more interesting.

A smiling person at a laptop sits between neon glowing app icons labeled "opus" and "fable," comparing two AI creative tools.

Claude Opus 5 vs Fable 5: Real Workflow Costs

Dev Kapoor1 month ago

AI. Dev Kapoor1 month ago

Claude Opus 5 vs Fable 5: Real Workflow Costs

Nate Herk ran Claude Opus 5 and Fable 5 through real agentic workflows. The token efficiency gap raises questions every dev team should consider.

Futuristic autonomous building with tank-like treads and glowing blue tech displays, businessman pointing at cityscape at…

Replit's Self-Driving Company Blueprint Explained

Dev Kapoor1 month ago

AI. Dev Kapoor1 month ago

Replit's Self-Driving Company Blueprint Explained

Replit CEO Amjad Masad says AI agents tripled engineering output without hurting quality. Here's what the "self-driving company" model actually requires.

AI Agents That Fix Slow Code Before You Notice

Bob Reynolds1 month ago

AI. Bob Reynolds1 month ago

AI Agents That Fix Slow Code Before You Notice

May Walter of Hud built an AI agent that hunts production performance problems weekly and hands engineers verified fixes. Here's what that actually looks like.

OpenAI GPT-5.6 promotional graphic with bold white text on blue digital background and yellow banner highlighting "Mastered…

GPT-5.6 and Codex: What the Hype Tour Reveals

Dev Kapoor2 months ago

AI. Dev Kapoor2 months ago

GPT-5.6 and Codex: What the Hype Tour Reveals

Julian Goldie's GPT-5.6 tutorial maps a genuinely new agentic workflow — but what it leaves unsaid about open source and agent governance matters just as much.

Man with surprised expression against black and white spiral background with text "CODE LESS LOOP MORE

AI Coding Agents That Run Their Own Loops

Marcus Chen-Ramirez2 months ago

AI. Marcus Chen-Ramirez2 months ago

AI Coding Agents That Run Their Own Loops

Developer Theo explores a shift in AI coding workflows: instead of prompting agents yourself, you design loops that let agents prompt each other autonomously.

Google AI Edge Gallery interface displaying Gemma-4 12B-it model with bold white text overlay reading "GEMMA-4 12B IS…

Gemma 4 12B Brings Local Agentic AI to Laptops

Yuki Okonkwo3 months ago

AI. Yuki Okonkwo3 months ago

Gemma 4 12B Brings Local Agentic AI to Laptops

Google's Gemma 4 12B is a multimodal local AI model built for real agentic workflows on 16GB laptops—here's what the architecture actually means.

Man in beanie at desk pointing to "Senior Partner" nameplate with red X over "Junior Partner" sign, bookshelves behind him,…

Stop Prompting. Start Questioning Your AI Agent

Rachel "Rach" Kovacs3 months ago

AI. Rachel "Rach" Kovacs3 months ago

Stop Prompting. Start Questioning Your AI Agent

AI strategy creator Nate B Jones says prompt engineering is dead. His 'AI Question Method' has real merit—but there's a data privacy conversation he's skipping entirely.

Smiling person next to "Game Over" screen displaying a task scheduling interface with loading icons

Claude Code's Scheduled Tasks: AI That Works While You Sleep

Zara Chen6 months ago

AI. Zara Chen6 months ago

Claude Code's Scheduled Tasks: AI That Works While You Sleep

Anthropic just gave Claude Code the ability to run tasks automatically on a schedule. Here's what that means for AI automation—and where it gets tricky.