Open Knowledge Format vs RAG: Why Your Agent Should Read a WikiOpen Knowledge Format vs RAG: why a markdown wiki beats vector search for facts your agent already knows.11 min read·designly.hashnode.dev2Aug 23
How DeepSeek Harness Saves Tokens by Not Editing HistoryDeepSeek Harness never edits sent tokens. A still prefix cache stays warm, so the same agent input lands in the cheap column, up to 30× less.13 min read·designly.hashnode.devAug 18
Why await Doesn't Make JavaScript Run in OrderLearn why await only pauses one async function—not the whole program—with a two-function example, log timeline, and when Promise.all() is better.6 min read·designly.hashnode.devAug 16
How to Automate Scheduled X Posts with Codex and xurlLearn how to automate scheduled X posts with Codex and xurl using a fixed-account skill, duplicate checks, and a safe publishing boundary.13 min read·designly.hashnode.devAug 16
Don’t Waste Your Money on GitHub Actions—Do This Instead!Stop overspending on GitHub Actions. Learn how to build a disposable EC2 build server that runs faster, costs pennies, and deploys in minutes.8 min read·designly.hashnode.devOct 8, 2025