Fazle Rahman

you shipped something and nobody knows yet. you could write about it, but who'd read it? a new blog has no readers, and search and ai answers don't know it exists. meet hashnode pro and growth. you write, your agent handles the rest, and you see if chatgpt and gemini cite you.

you don't write alone anymore. you draft posts with claude now. people find your products when chatgpt cites you. your blog wasn't built for either. so we rebuilt hashnode. it's built for writing with an agent in the room, and for readers who bring theirs. this is the new hashnode. 1.3m+ blogs have started on hashnode. if you had one, it's still here. so are your posts. and if you mapped your own domain before pro existed, that still works too. here's how it feels now. you're in claude or chatgpt, talking through something you figured out at work. you say "save this as a draft on my hashnode blog." and it's there. your blog's connected over mcp, and you only signed in once. then you open the draft. you cut what's wrong, rewrite the bits that don't sound like you, and hit publish. if you live in the terminal, the cli and the agent skill do the same thing from a script or a coding agent. every post goes out two ways. people get a page, and their assistants get clean markdown. just add .md to any post url. one thing we really don't want is hashnode turning into a pile of ai posts nobody reads. so we run spam agents 24x7 now. they're 2000% more effective than before. we built them on jev, trained on all the spam we've caught over the years. "why not just have claude build me a blog in ten minutes?" honestly, you can. but you'll be writing in mdx and pushing to git, it won't tell you when chatgpt cites you, and you'll be the one keeping it alive. every time google or the ai crawlers change the rules, you're the one catching up. we take care of all of it: - you write in a real editor, from anywhere. no git, no build, no deploy - every post already ships with clean markdown, structured data, sitemaps and rss. when search or ai rules change, we update every blog at once. you don't touch a thing - on growth, we ask chatgpt, claude, gemini and perplexity your questions every day and show you when they cite you. and who they cite when they don't - we handle hosting, images and upgrades. you just write if you write on your own: - it's free to start, and your blog's live in a minute - people can follow you and comment, so you build a name in public - you can sell your products and services through what you write - your words stay yours. export everything to markdown whenever you want if you're a team: - bring everyone into one publication. admins, authors and contributors, with a review queue so nothing ships by accident - your agents work like teammates. they submit drafts, and someone on your team approves - you can see which questions your customers ask ai, and whether your posts get cited - fun fact: our own changelog runs on hashnode what keeps the lights on: - it's free to start - pro is 5 dollars a month per seat. you get your own domain, the agent tools, ai in the editor and the api - growth is 34 dollars a month with pro included. that's where citation tracking and ai traffic live under the hood, it's all rebuilt from scratch. one honest note: the graphql api is pro now, and not everyone loved that. we're still a small startup, and we had to get the cost and the misuse under control. we'll be a lot more active here on x from now on, posting what we ship and the best stuff people write on hashnode. so bring your agents, bring your team, and bring your creativity to hashnode. share it with a global audience.

Everyone is suddenly building an AI software factory: a system where coding agents take a ticket to a verified pull request with no human in the middle. The term is from Hitachi in 1969, and this is its third revival. What strikes me about the category is how converged it already is. Devin, Factory, 8090, and FactoryKit all run the same five stages: intake, isolation, implementation, verification, PR. When four vendors independently arrive at one architecture, that usually means it's durable. What's missing is measurement. There is no public benchmark for ticket-to-merged-PR reliability across any of these products. The naming is outrunning the measuring, and buying decisions are running on demos. Full disclosure, we build one of the four, so I wrote this with the gaps in as much detail as the pitch: hashnode.com/blog/ai-softwar…