botacode

Three things we thought were interesting in this release:

1) New browser sessions in most assistants don't retain (transaction) permissions between sessions 2) Assistants aren't 100% accurate in task completion reporting, yet 3) MCP 2.0 lets servers push updates to clients like ChatGPT plugins or Claude Code Connectors

The release also adds testing tools, opt-in actions, delivery records, revocation checks, bounded sandbox execution, and documentation for 13 other assistant behaviors we've tested for.

It's another small step towards more behavior-emulation-based tests to improve MCP and APIs performance on these new meta-browser tools.

Please do let us know if you, or your agent, have any feedback!

Are there options to replace Gemini with remote models that support ZDR?

Think I'd be willing to take a bit of a quality hit to at least have that even if it isn't fully local.

In a few years we'll cover all the categories! Thank you for taking a crack at it!

We only send your information to insurers we quote you with and do our absolute best not to spam (we send 2-3 reminders depending on policy type), our goal is to never call.

In California we specialize in harder-to-insure homes, i.e. stuff that will place with a non-admitted/surplus policy, the goal is to help keep people off FAIR.

RE: cancellation/non-renewal, these do happen but it could happen to your existing deal too unfortunately. No one will force you to switch if it isn't a good deal and our agents do their best to always advise to the user's best interest. Our goal is to retain you as a customer for life (our agents just optimize automatically for you every year!) rather than make a quick buck one year.

A lot of umbrella prices are somewhat parseable (think a simple-ish decision tree) vs auto and home prices which require reverse engineering rate cards to back into the pricing formulas.

Yes, folks come back at the end of their year. Most of the time their price remains the best (non-issue), when there are better options they switch. Carriers have been great partners so far since we bring them much more business than switches (and when the switches happen it's often because risk management wanted to reduce exposure in that region anyway).

We're eyeing nationwide expansion in 2027 or later this year!

They'll enforce the minimums even as a standalone policy, my understanding is it's that the umbrella always "sits" ontop of something. I.e., they want you to clear the other liability limits before they step in to provide coverage.

It is kind of a huge hassle, especially in states like CA or FL where a lot of carriers have withdrawn and the default bundle option isn't necessarily available. We went looking for high pain X feasibility and this is where we landed!

Emailed yah, thank you for the note!

To answer more directly, yes we do! Most of the umbrella coverage we offer though is of the unbundled variety.

This is great to hear, I'd count this as a success in our book!

After much trial and error, we've come to realize that trying to separate users from their existing insurance arrangements is very hard unless there's some sort of stark event that triggers the switch.

I.e., folks will usually only make a purchase with us if one of the following is true (even if they could save money or improve coverage):

- they're shopping for the first time and want a modern, online-first, service that avoids hassle

- their premiums have jumped

- they were non-renewed

Most users' experience of shopping for insurance has been historically so bad that they're very averse to optimizing it, even if 10m or so could save them hundreds (and in extreme cases thousands) of dollars.

Ironically one of my favorite acronyms

Thank you for the feedback, let's see if they'll let us edit it down a bit.