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.

hello

Hashnode now has an MCP server. claude mcp add --transport http hashnode-mcp mcp.hashnode.com/mcp Claude, ChatGPT, or Codex can now read and write your Hashnode posts directly. Requires a Pro plan. hashnode.com/changelog/2026-…

✅ We're back online! The issue has been resolved, and service is restored. Thank you for your patience, and we apologize for the inconvenience.

⚠️ We're currently experiencing technical issues. Our team is working to restore service as soon as possible. We apologize for the inconvenience and appreciate your patience. We'll keep you updated!

Shipped two things for the AEO toolkit. A ranked list of who else gets cited for the same question as you, and a card showing how much traffic ChatGPT, Perplexity, Gemini, and Claude actually send to your blog. Both on Growth Plan. hashnode.com/changelog/2026-…

The Growth Plan is now available: everything in Pro, plus an AEO toolkit for a flat $29 a month. Your next reader asks ChatGPT, gets one answer, and never sees a results page. The toolkit is built for that: - AEO score in the editor, eight checks before you publish - FAQ blocks that ship as structured data - Per-bot robots.txt toggles for AI crawlers, plus an llms.txt index of your posts - Freshness queue so you know what to update next - Daily checks on whether ChatGPT, Claude, Gemini, and Perplexity cite you Upgrade from your dashboard's billing page. Full details are on hashnode.com/pro under the Growth tab. 📖hashnode.com/changelog/2026-…

A clean explainer on what a background coding agent actually is, and how it differs from the tools people already have open. The framing that makes it click: sort AI coding tools by how often a human closes the loop. Autocomplete asks every few seconds. IDE agents like Cursor and Claude Code ask every few minutes. Background agents run in a cloud sandbox and ask once, at the pull request. Same models underneath. What changes is where the loop runs. The part I'd underline is what should arrive attached to that pull request. A diff on its own puts the whole verification burden back on the reviewer. The checks it passed, a self-review of the diff, and a recording of the change working in a real browser are what make review quick enough to be worth doing. There's also a good point on security: safety comes from isolation and scope, not from trusting the model to behave. factorykit.ai/blog/backgroun…

If you're weighing whether to build an AI software factory in-house, this is the build log to read first. "The coding agent is the part you do not build." The project is the seven stations around it: isolated execution, snapshot templates, credential handling, git and PR orchestration, a server-owned run loop, live observability, and verification. Verification is the one everyone underestimates, since a green CI run tells you nothing about whether a user-facing change actually works. Two costs that never reach a budget line. Review attention grows faster than anything on an invoice. And an internal factory is a product with exactly one customer, so somebody owns it for as long as the company runs it, and that name usually gets decided by accident. The other useful reframe: running cost scales with how many tasks you queue, not how many engineers you employ. sandeep.dev/blog/what-a-soft…

Sandeep puts the line between agentic coding and vibe coding in the place that actually decides anything, which is where the review happens. "Both start with a prompt. Only one of them ends with somebody reading the diff." The post comes with three weeks of numbers from a real repo. Agents opened 69 of the 99 PRs that merged, 56 of those went in unchanged, and 13 needed a human to correct them. The useful finding is what those 13 had in common. Every one was a task where nobody had written down what finished looked like, which makes an 18.8% correction rate a measure of the task description as much as of the agent. There's also one example that justifies the whole review gate: an agent shipped image upload and left the files publicly readable. Review caught it inside a day. sandeep.dev/blog/agentic-cod…

AI software factory covers four different purchases, and vendors rarely tell you which one you're being shown. Buy a platform and you get the plumbing between the stages, then you integrate it into your own stack. Assemble one and you pick the sandbox, the coding agent, the verification layer and the credential broker separately. Self-host the lot if compliance says code cannot leave the network. Or have one built inside your environment and handed over to you. The stages are the same in every case: intake, isolation, implementation, verification, pull request. What changes is who does the integration work, and how long you wait for the first PR. Two things I'd check before sitting through a demo. Isolation is harder than it looks and gets underestimated in almost every plan. And assembled stacks tend to drop verification, which leaves you with an agent that opens pull requests nobody trusts. There is also no published first-attempt merge rate from anyone, so you cannot compare reliability across vendors yet. The tools available at each layer: hashnode.com/blog/ai-softwar…

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…