Healthcare software was designed for humans. Multi-step, nuanced workflows: prior auth submissions, EHR note creation, eligibility verification. The kind of work that can't be reduced to an API call. That's what AI agents in healthcare are being asked to automate. And the infrastructure to do it reliably doesn't exist off the shelf. We build it: A coding agent to generate automation scripts, fully managed infrastructure to run them at scale, and a maintenance agent to keep them working as portals and EHRs change. Today, we're announcing our $5M seed round, backed by Floating Point, @MeridianStCap, Twine Ventures, @refractvc and angels like @zacharylipton (CTO, Abridge) and @dps (fmr. CTO, Stripe). If you're building AI agents that need to operate payer portals or EHRs, we'd love to talk. And we're hiring!

I found the actual smoking gun

Very wrong, very dangerous You want your APIs to do the exact same thing, every time AI is great at many things; reproducibility is not one of them

Today, we’re launching Automatic Password Updates. Many websites require you to update your password every 90 days and historically, we would flag this but didn’t automatically address this for our customers.  CloudCruise now:     •    triggers an automatic password update     •    stores it in your CloudCruise vault      •    re-runs the automation seamlessly

when an enterprise prospect wants to start a POC but has no idea what success looks like

The degree to which you are awed by AI is perfectly correlated with how much you use AI to code.

thinkingBudget: 0

what my gf thinks my relationship with claude is

noticing a shift in healthcare automation, with the next wave moving beyond building workarounds to focusing on making systems agent-accessible

this and 6 agents to check in on at the 40km coffee break

giving claude access to turbotax

Every healthcare workflow can be mapped to an automation script. The bottleneck is maintaining it in an environment where UIs and business requirements change. Traditional computer use runs an agent loop on every task. We're building an autonomous system that generates the script once, executes deterministically, and self-heals when something breaks.

Your future users are AI agents. Unlike humans, they'll actually tell you what's wrong with your product

I can confidently say this is the wildest popup I've seen all year

The Agent axioms: 1. There is always a workflow (it may be trivial such as the implicit single step workflow) 2. Workflows may contain agents (LLMs with tools in a loop) 3. Tools are workflows ((even if trivial per 1) which can contain agents per 2)