Anthropic's domain usage (there's claude.com, claude.ai, console.anthropic.com, platform.claude.com, claudecode.io forwarding to codeagents.app which errors) and authentication approach have been lacking a lot; hope this isn't a verdict on their use of agentic coding.

Example: I had two orgs with similar names, one I set up myself and another my employer set up. Logged in via SSO. Once I deleted the one I created myself, I could not log in anymore with the notice that the org was scheduled for deletion. Could also not contact support as that required a login. Only when the org was deleted after a week and my employer deleted me and reinvited me I could access it again.

Quite the shitshow for a company worth a couple hundred billion.

One example: I let the agent culminate the essence of all previous discussions into a spec.md file, check it for completeness, and remove all previous context before continuing.

Out of curiosity, do you expect that freedom.gov will contain socialist, communist, extreme left-wing or islamist point of views?

I think the defense is that it's the fault of the politicians (CDU/CSU, actually), as they are the ones allocating funds towards train infrastructure. The Deutsche Bahn is state-owned in all but name (which was one of the major fuckups of the last red-green government).

The German Personalausweis seems to offer something like this (basically returning a bool indicating whether a user is below or above a certain age), but it seems as if the service indicates which data it requests from the ID card. As a user, I would not be able to state that this or that porn site should only see this age verification. Not sure how the requestable data are in turn requested by the service.