One caveat to alerts (and automatically acting on alerts) is that there are delays[0] between costs being incurred and alerted. I can't find a Google source for what the delay is, but a source online say it could be "24 hours [to] a few days."[1]
This has been a major reason why I reach for OpenAI models before Gemini, but also why I'd rather use services like RunPod for training jobs. For a small boostrapped company like mine, it feels terrifyingly easy to rack up a company-ending AI bill.
The cloud companies try to limit these accidents through cranking your quotas down to nothing, but this also means that my small company can't just whip up 8xH100 easily without major ceremony, and I have routinely been rejected the GPUs quotas I needed for projects.
Accidentally leaving that kind of node on for the 24 hours that it might take to get an alert would rack up a $2,000+ bill, compared to $500 on RunPod, which will also stop the instance when you run out of money.
I've loved working with major cloud providers at growing VC-funded startups that have credits, TAMs and bigger budgets for errors. But hyperscalers are fairly difficult for a pre-scale bootstrapped business, and arguably not designed or optimized for it.
I did just manage to dig up a source that says these things are somewhat implemented in iOS 18 with illustrative screenshots rather than actuals, and it seems to be implemented but currently janky:
- On iOS, rich cards have a message length limit of 144 characters. (Implies this is not a limitation on Android.)
- On iOS, multi-CTA might fold some of the options away. So you might give 4 options and it renders 2 options and makes you use a drop-down for the others.
- On iOS, carousels display as cards, which might not be as obvious to interact with.
Potentially improved in iOS 26. It's a little hard to work out the state of this, and of course not trivial to test without joining some kind of partner ecosystem.
I'm pretty unclear about how the experience they showcase in the video would work on iOS. Maybe Android has APIs for this, but on iOS it looks like RCS just supports green-bubble messages, links and files/multimedia. But in the demo they show multi-choice cards, carousels, cards with buttons, and reply auto-suggestions.
Also, someone correct me if I'm wrong, but it also looks like this needs to be agent-initiated, ie. you can't add a "Text us" button that will take you to this experience. (But you could capture a phone number, and text them _iff_ they have RCS available and enabled.)
Overall, seems questionable whether this is worth integrating if the experience is so fractured across platforms and many people might not even have RCS. The concept of a platform for rich messaging across platforms sounds good though.
This has been a major reason why I reach for OpenAI models before Gemini, but also why I'd rather use services like RunPod for training jobs. For a small boostrapped company like mine, it feels terrifyingly easy to rack up a company-ending AI bill.
The cloud companies try to limit these accidents through cranking your quotas down to nothing, but this also means that my small company can't just whip up 8xH100 easily without major ceremony, and I have routinely been rejected the GPUs quotas I needed for projects.
Accidentally leaving that kind of node on for the 24 hours that it might take to get an alert would rack up a $2,000+ bill, compared to $500 on RunPod, which will also stop the instance when you run out of money.
I've loved working with major cloud providers at growing VC-funded startups that have credits, TAMs and bigger budgets for errors. But hyperscalers are fairly difficult for a pre-scale bootstrapped business, and arguably not designed or optimized for it.
[0] https://docs.cloud.google.com/billing/docs/how-to/disable-bi... [1] https://support.terra.bio/hc/en-us/articles/360057589931-How...