*This is a submission for the [Kaggle Benchmarking Challenge](https://dev.to/challenges/kaggle-2026-09-23)* ## What I Benchmarked A while back I spent time manually poking at Gemini, ChatGPT, and Claude with the same trick: ask a multi-step question, then feed the model a plausible-looking mid-rea...
Read articleI have Claude Code operate macOS apps in the background: fill a form, pick an option from a pop-up, run a calculation. With the MCP server I built on top of cua-driver, beans-picker, a typical task in my benchmark ran 1.8x faster and cost 85% less than with cua-driver alone (median 28.1 s vs 49.7 s,...
Read articleIn March 2026, a financial services company discovered that their customer-facing AI agent had been quietly leaking internal pricing data — for three weeks before anyone noticed [1]. There was no buffer overflow. No SQL injection. No misconfigured API. Nobody breached a server. The agent leaked the...
Read articleThe honest constraint behind everything I build is that there is one of me. A portfolio of sites doesn't care about that. Each one wants features, fixes, content, and maintenance, and the naive way to run several at once is to context-switch between them until nothing gets real attention. So I stopp...
Read articleWe started a company with $20 and one rule: the humans stay out of the loop. Five Claude Code agents run it from a private GitHub repo. Scheduled workflows wake them up, they do one job each, and they write down what they did. The ledger and the journal are public at https://www.leymish.com. This p...
Read articleI have a bookmark folder called `prompting`. Forty-one tabs in it. "The 12 prompts that 10x your engineering." "Context engineering for agents, explained." "The system prompt that changed how I ship." A course I finished at 1am, certain I'd finally cracked the thing — that if I just learned to *ask...
Read articleAI can now write the feature. Then AI can write the tests. Then AI can open the pull request. Then AI can review the pull request. Then AI can fix the review comments. And finally, a developer clicks: **Approve.** That workflow sounds incredibly efficient. It also creates a very uncomfortabl...
Read articleSEO automation is increasingly being framed as a **workflow design problem**, not a choice between manual work and autonomous AI. A recent signal from [Search Engine Land's official X account](https://twitter.com/sengineland) highlights the practical question: which SEO tasks should run on rules, wh...
Read article> **TL;DR:** A vibe is compressed experience: pattern recognition that shows up as a feeling before it shows up as an explanation. It's one of the oldest tools our species has. Vibe coding goes wrong when the feeling is treated as the finish line. The fix is the other half of the loop: **vibe → buil...
Read articleWho called your API last? For us, the honest answer is more and more often an agent. Claude Code debugging a flow. An assistant looking up an order. Someone's custom GPT. Our tools still assume a human pressing Send. This post is about that gap. How we ran into it ourselves, how most teams han...
Read article