#ai-agents

Where My Level 5 Software Factory Doesn't Cut It Yet

My Level 5 software factory ships code unattended, until it hits CI limits, 50-node plans, or reward-hacking loops. Three lessons from recent failures.

Diversifying Your AI Tooling: Why Lock-In Is a Mistake

I use five AI agent platforms daily. Here's why diversifying your tooling strategy matters for learning, money, and your actual workflow. Learn how to avoid lock-in.

Meet Sadie: Building an Almost 100% Local Family AI

We built a custom, almost entirely local family AI named Sadie. Powered by an AMD inference box, HomeAssistant, and a tailored Open WebUI fork.

The Focus Tax: How Antigravity Cures Context Switching

The average developer loses 20% of cognitive capacity per context switch. See how Antigravity's asynchronous tools and subagents cure the focus tax.

From Tickets to Specs: How AI Agents Heal the PM-Dev Divide

Traditional PM-developer handoffs are a game of telephone. Spec-driven development with AI agents turns requirements into a compilable bridge.

TOON vs JSON: Why AI Agents Need Token-Optimized Data Formats

TOON cuts LLM token costs 50% vs JSON. Why AI agents need token-optimized formats like TOON & markdown. Deep dive for developers building with AI.

MCP Context Bloat: When Your AI Agent Gets Dependency Hell

Running too many MCP servers creates the same problems we learned to avoid with dependencies. Here's what we're doing about it.

When Your AI Agent Decides to Skip the Tests

Comparing two approaches to AI coding: paranoid infrastructure engineer versus move-fast entrepreneur. Both are right.

1,189 AI Agents and Most of Them Don't Matter

The AI agent ecosystem is massive and fragmented. Here's how to separate tools that solve real problems from expensive distractions.

The Boring Middle: Why AI Agents and Shell Scripts Both Win

Kelsey Hightower's right: AI agents and shell scripts both have their place. Here's why the future isn't either/or—it's the boring middle.

AI Agent Feedback Loops: How to Monitor and Validate Autonomous Agents

Learn how to build feedback loops for AI agent teams. Covers validation, monitoring, error handling, and CI/CD patterns for autonomous agents.

Why Experienced Architects Will Orchestrate AI Agent Teams (Not Write More Code)

The AI replacement narrative gets it backwards. Junior developers get faster with Copilot. Senior architects are learning to orchestrate fleets of specialized autonomous agents.