# Notes on Claude Code, AI agents and the web.

Page 2 of 12. Hands-on posts on Claude Code, MCP, AI agents, Next.js and TypeScript, plus honest tool comparisons from shipping software for clients.

RSS: https://alexcloudstar.com/rss.xml

- [GPT-6 Astra Review: The Best Agent Anyone Has Shipped, and the First That Hides Its Work](https://alexcloudstar.com/blog/gpt-6-astra-review-benchmarks-pricing-2026/): OpenAI shipped GPT-6 Astra on September 3 at $10 in and $50 out, the same headline price as Claude Fable 5.1. The benchmarks are a real jump, the cache price is four times higher, and the model uses a reasoning technique that makes its chain of thought harder to monitor. Here is the whole picture. (Sep 2026)
- [I Built beseen.so Because Every AI Visibility Tool Sells You a Thermometer and Calls It Medicine](https://alexcloudstar.com/blog/beseen-so-ai-visibility-tool-launch/): Yesterday I wrote that every AI visibility tool tells you a competitor got named and none of them tell you what to change. beseen.so is what I built about it: it finds the prompts where assistants name someone else, writes the actual page rewrite, and re-checks whether the answer moved. (Sep 2026)
- [How to Measure AI Visibility When 68% of Searches End Without a Click](https://alexcloudstar.com/blog/zero-click-search-2026-measuring-ai-visibility/): Zero-click searches hit 68.01% in early 2026, up from 60.45% in 2024. The harder problem is that the traffic you are losing to AI answers is invisible in Google Analytics by design. Here is how to actually measure whether assistants are naming you, and what it costs. (Sep 2026)
- [Programmatic SEO in 2026: What Google Killed in March, and What Still Prints Traffic](https://alexcloudstar.com/blog/programmatic-seo-2026-indie-hackers/): Google stripped 50 to 80 percent of traffic from low-value programmatic sites in March. Meanwhile Zapier still pulls 16 million monthly visits from 50,000 integration pages. Here is the difference between the two, and how to build the second kind without tripping the scaled content abuse policy. (Sep 2026)
- [Claude Fable 5.1 Review: Benchmarks Went Up, but the Cache Price Cut Is the Real Release](https://alexcloudstar.com/blog/claude-fable-5-1-review-cache-pricing-2026/): Anthropic shipped Claude Fable 5.1 and Mythos 5.1 on September 1 at the same $10 in, $50 out price as Fable 5, then cut cache reads by 75%. Here are the benchmarks that moved, what the pricing change actually does to an agentic bill, and whether it is worth switching. (Sep 2026)
- [Merchant of Record in 2026: Paddle vs Stripe vs Polar, and the Lemon Squeezy Question](https://alexcloudstar.com/blog/merchant-of-record-indie-saas-2026/): Polar raised its rates 25% this year. Lemon Squeezy is quietly being folded into Stripe. Paddle still charges 5%. Here is the actual merchant of record math for a solo founder in 2026, and the honest answer about when paying that tax is worth it. (Sep 2026)
- [Next.js 16: Instant Navigations and Cache Components in 16.3](https://alexcloudstar.com/blog/nextjs-16-3-instant-navigations-cache-components/): Server Components made Next.js apps fast to render and slow to click through. Next.js 16.3 fixes that with Instant Navigations, Partial Prefetching, and a client-side cache built on the use cache directive. Here is what actually changed, what it costs you to adopt, and whether you should turn the flags on today. (Aug 2026)
- [justship.now Is My New Front Door: Why a Curated Tools Directory Beat Out Another SaaS](https://alexcloudstar.com/blog/justship-now-curated-tools-directory-indie-hackers/): I just moved justship.now into the number one project slot on my own portfolio, ahead of makers.page. Here is what it actually is, why a curated tools directory earned that spot, and why I think curation beats crowdsourcing for this specific job. (Aug 2026)
- [Startup Directory Submissions in 2026: What Actually Moves the Needle for SEO](https://alexcloudstar.com/blog/startup-directory-submissions-seo-2026/): Every "submit your startup" listicle promises hundreds of free backlinks. Most of that advice is a decade out of date. Here is what actually happens to your domain authority when you submit to directories in 2026, and which ones are worth your afternoon. (Aug 2026)
- [outbid.lol and the Pay-to-Rank Leaderboard Boom: Why I Built ownthe.day Differently](https://alexcloudstar.com/blog/outbid-lol-leaderboard-trend-ownthe-day/): outbid.lol made six figures in under 48 hours and spawned a dozen clones overnight. I break down how the pay-to-rank leaderboard trend actually works, why it exploded, and why I built ownthe.day on a different mechanic on purpose. (Aug 2026)
- [I Built roastme.gg, a Site Where You Pay to Get Publicly Roasted by AI](https://alexcloudstar.com/blog/i-built-roastme-gg-pay-to-get-roasted-by-ai/): I shipped a site where you pay to get publicly roasted by AI, ranked on a wall by how much it hurt your wallet. Then I ran it through ChatGPT live search to see if it actually shows up for anyone who is not already looking for it by name. (Aug 2026)
- [mybutler: A Local-First AI Assistant That Remembers Without a Cloud Account](https://alexcloudstar.com/blog/mybutler-local-first-ai-assistant/): I had a hundred open chats across ChatGPT and Claude and no idea what was in half of them. So I built mybutler, a menu bar app that answers privately through a local Ollama model and remembers what matters outside of any single chat. (Aug 2026)
- [I Just Shipped My First Chrome Extension (And It Was Harder Than the Code)](https://alexcloudstar.com/blog/i-just-shipped-my-first-chrome-extension/): What building and publishing XPilot taught me about Manifest V3, OAuth, and the gap between "it works on my machine" and "it works in the Chrome Web Store." (Jul 2026)
- [Claude Fable 5 Review: Is It Worth 2x the Price of Opus 4.8?](https://alexcloudstar.com/blog/claude-fable-5-review-benchmarks-developer-guide-2026/): Anthropic shipped Claude Fable 5 yesterday, the first Mythos-class model cleared for general use. It posts 80.3% on SWE-Bench Pro, costs double Opus 4.8, and ships with a sibling, Mythos 5, that has the guardrails off. Here is what actually changed and whether you should switch. (Jun 2026)
- [Markr: Mark the Moment While You Record, Not After](https://alexcloudstar.com/blog/markr-mark-the-moment-while-recording/): I always wanted to do YouTube. I just hated the part where you rewatch a 30-minute recording twice to find your mistakes and pull clips out of it. Markr is a small open-source app that lets you drop timestamp markers while you record, so you stop rewatching everything later. (Jun 2026)
- [2,159 Cold Messages, 4 Replies: What Starting on Your Own Actually Looks Like](https://alexcloudstar.com/blog/2159-cold-messages-4-replies-starting-on-your-own/): The romantic version of starting a startup skips the part where you send 2,159 cold messages and get 4 real replies. This is five weeks of the actual grind: the silence, the red flags, killing an idea I liked, and the absurd moment I built a product to help me look for a product. (Jun 2026)
- [Modern CSS in 2026: The JavaScript You Can Finally Delete](https://alexcloudstar.com/blog/modern-css-2026-features/): Tooltips, accordions, theme toggles, dropdown positioning, scroll animations, responsive components. For years we reached for JavaScript to do all of it. Modern CSS in 2026 does most of it natively, and the support numbers are finally good enough to ship. Here is the JavaScript you can delete and the CSS that replaces it. (Jun 2026)
- [Svelte 5 vs React in 2026: An Honest Comparison After Shipping Both](https://alexcloudstar.com/blog/svelte-5-vs-react-2026/): Svelte 5 introduced runes and turned the reactivity question into a real debate again. I built production apps with both Svelte 5 and React 19 this year. Here is the honest comparison: bundle size, the runes vs signals model, the TypeScript friction nobody mentions, hiring, and when each one is actually the right call. (Jun 2026)
- [Background AI Coding Agents in 2026: When to Delegate Work to Async Agents](https://alexcloudstar.com/blog/background-ai-coding-agents-2026/): The average coding agent session went from 4 minutes to 23 minutes in a year, and a lot of that work now happens without you watching. Background agents open a draft PR while you do something else. Here is how I decide what to hand off, what to keep local, and how to not drown in agent-generated pull requests. (Jun 2026)
- [The Best Background Coding Agents in 2026: Codex Cloud vs Cursor vs Copilot vs Claude Code](https://alexcloudstar.com/blog/best-background-coding-agents-2026/): Every major coding tool now ships an agent that runs in the cloud and opens a pull request while you do something else. They look the same from the outside and behave very differently in practice. I ran real work through Codex cloud tasks, Cursor cloud agents, the Copilot coding agent, and Claude Code async to figure out which one to reach for and when. (Jun 2026)

- [Newer posts](https://alexcloudstar.com/blog/)
- [Older posts](https://alexcloudstar.com/blog/3/)