Is it just me or is Cloudflare releasing like 5 new products a day right now?

"Agents Week" https://blog.cloudflare.com/welcome-to-agents-week/

> CloudExit Pro is a service of Avallark Services LLP

Nothing suspicious here…

why does it have to be suspicious. Its a services offering that we have.

> why does it have to be suspicious. Its a services offering that we have.

It's difficult to read good intent in the original comment when the text of the comment says "these guys" as if the account (your account) is endorsing the service rather than representing itself as the provider of the service.

Honestly, it might just be worth deleting and trying again, this time with an honest blurb from your account about the mission rather than pretending to endorse your own product.

> No blueprints, no permits, no audits.

Where I live, permits are required for all sheds, and for those above a certain size you have to submit blueprints.

Agreed. The over-confident quipy-ness of the description reads like an LLM. Though fwiw, I’m a lawyer and it took me a minute to parse this.

Gift link: https://www.nytimes.com/2026/03/30/opinion/giving-pledge-phi...

Agreed! And shout-out to the people at CourtListener (the site hosting this PDF), who make millions of US court documents freely available to the public.

Serious question: Did you use AI to write this or do you just sound like an LLM after having used them so much?

I’m getting pretty decent at spotting LLM text. This doesn’t contain the obvious tells at least.

The fact this needs to exist seems like a UX red flag.

Reminds me of Vercel's Rauch talking about his aggressive 'any UX mistake is our fault, never the user's' model for evaluating UIX. (It is/was Guillermo who says that, right?)

This should be all of Information Technology’s take. Your computers get hacked - IT’s fault. Users complain about how hard your software is or that it breaks all the time - IT’s fault.

The fact users deal with almost everything being objectively not very good if not outright bad is a testament to people adapting to bad circumstances more than anything.

It's a CLI. CLIs have man pages and cheat sheets. That's not a UX failure, that's the format. The same argument would apply to git, ripgrep, or ffmpeg.

The actual complexity in Claude Code isn't the commands, it's figuring out a workflow that works for your codebase. CLAUDE.md files, hooks, MCP servers, custom skills. Once you have that set up the daily usage is just typing what you want done.

Similar to prompting hacks to produce better results. If the machine we built for taking dumb input that will transform it into an answer needs special structuring around the input then it's not doing a good job at taking dumb input.

it doesn't need to exist, its all in claudes help, and easily discoverable.

> Ctrl-F "help"

> Ctrl-F "h"

> 0 results found

Interesting set of shortcuts and slash commands.

This. TUIs are not the correct paradigm for agentic operations. They are too constrained, and too linear.

You have a sad narrow point of view about what UX can be.

Enlighten me?

I recently left a large law firm where Word took upwards of 30 seconds to launch. To be fair, I think the issue was the many large and buggy plugins that came preinstalled on everyone's machines. But it still left me glowering at the Microsoft Word logo multiple times a day.

Adding this to my list of ~beautifully~ designed things to buy when I win the lottery.