PinnedAlex Rozdolskyi·Feb 1210 Wild Things People Actually Built with OpenClawThe wild, expensive, occasionally terrifying things people built with autonomous AI
InLevel Up CodingbyAlex Rozdolskyi·Apr 29OpenClaw vs Claude Code: Which Agent Layer Are You Actually Choosing?One is a persistent, self-hosted runtime across channels. One is an agentic coding tool with deep repo execution. They overlap less than…
Alex Rozdolskyi·Apr 28OpenClaw vs Hermes Agent: Ecosystem Reach or Learning DepthTwo open, self-hosted agent runtimes. Same problem class, different center of gravity — and the choice is mostly about what you want the…
Alex Rozdolskyi·Apr 27The Three Memory Layers Every Agent Team Needs (And the Specific Failure You Get Without Each)Most agent failures are memory architecture failures wearing a prompt-quality mask.
Alex Rozdolskyi·Apr 253 Things You Might be Building When You Think You’re Building an Agent (and which one you actually…Every option looks like a loop with tools until you define what has to be true for the run to have succeeded.
InLevel Up CodingbyAlex Rozdolskyi·Apr 24I Let an AI Agent Run My Morning for 30 Days. Here’s What It Actually DidWhat actually changes when AI stops answering questions and starts running your workflow
Alex Rozdolskyi·Apr 2410 Prompting Mistakes That Only Show Up in Multi-Agent Systems — And How to Fix Each OneEvery vague word in your system prompt is a decision your agent makes without you.
Alex Rozdolskyi·Apr 23What OpenClaw Gets Right That Most Agent Setups Get WrongFive design decisions that look obvious in hindsight.
Alex Rozdolskyi·Apr 22Build the Content Company from Scratch with Paperclip AIRoles, config, delegation chain — and the three things I got wrong before it worked.
Alex Rozdolskyi·Apr 21Paperclip Lets You Build an AI Company, Not Just an AI WorkflowHere’s the difference — and five real patterns worth stealing.
