_puk

If you build your platform well, then you can execute fast, but also safe.

I push "money and data are sacred"; if we lose either of those, someone cries. Build the platform slow and fast. Governance, scaling etc sits here.

Provide reference APIs and let the product team one shot whatever they want and need, build fast and experimental, but your platform enforces constraints.

Best of both worlds (though feels like we're back in backend vs frontend development)

Thanks for this.

Built this myself using Gemma4, but the branching is neat. Will have to try it.

If you're packing the questions into the branches, is there a chance that the ordering of the questions can change the probability of each output?

I see you have packs, but as close to deterministic as possible is what I'm after.

It's all moot soon:

Updates to your Google AI Plus plan

We wanted to let you know about changes to the models that you can access with your Google AI Plus plan.

Starting on 1 3 N o v e m b e r 2 0 2 6 , the ability to select Pro models in both the Gemini app and AI Mode in Google Search will only be available to Google AI Pro subscribers and above. You'll still have access to our latest Flash-Lite model and Flash, built for speed and intelligence. Your previous chats using the Pro model can be continued with a different model.

To learn more about these changes, you can visit our Help Centre article for additional details. You can manage or cancel your subscription at any time.

Thank you for being a Google AI Plus subscriber.

Yeah, and then who maintains it?

Maintaining vibe coded software is going to become hours spent with Claude not your users.

That's going to be the difference. It takes nothing to rebuild the software, but listening to users, iterating, handling issues. That's boring.

The ones that win will be the ones that stay the course, not the ones that were built the quickest.

If you've got 9 coders, you've at least got a business idea and some financial backing.

Get it out quickly, market it, iterate it. That hasn't changed. Just the speed of iteration before you go from product to product that sells.

Once you know what sells, then again, it takes far less time to rebuild it well if you need to.

This may be small nuclear team vs sprawling org difference.

This process works so well in a team that are all pushing together.

Moving the ticket along and a slack to the effect of "this one is quick and easy" Vs "this one's a bit gnarly, happy to jump on it with someone" generally sees PRs reviewed very quickly.

A pleading cat gif is usually enough as a reminder.

A well oiled team is working to deliver customer value (internal or external). I've been lucky enough to have had a few teams of incredibly good engineers over the years. So much gets done.

I can see it not working so well in a team of "individuals" focused on their own performance and "personal responsibility" solely for their bit.

The kind of teams that throw everything over the wall to an individual making a build gate go/no-go decision perhaps.

Given they probably need to go through layers of management, across teams, and go through relevant testing to adjust the LLM prompt, this was probably a nice quick and flexible way to create a "shadow" prompt.

Is that not the epitome of the classic mid life crisis?

You hit a point in your life, reflect back on where you'd thought you'd be when you were in your early 20s, and think.. shit.. what I do all of this for?

This isn't even a flippant comment (especially given the subject matter); being at this age and thinking "I imagined it would all be easy by now" does hit home.

The obvious fork is "can frontier models stack a dishwasher to my wife's exacting standards".

I can't. So that would surely be proof of AGI.

They have trillions..

Lots of people would have happily taken GPT-4o as good enough for a lot of use cases a year ago and not lived to regret it.

Interestingly if Google did release readily available video models then they'd likely be dealing with an order of magnitude of scale in the same way GitHub has had to.

Causing less content to be uploaded, when you are clearly the gorilla in the room, looks to be a wise strategy not a trade off.

The ease of building highlights the mental overhead of maintenance for me.

This is why SAAS is here to stay. Yes, I can one shot it, but then I've got to maintain it, and I want to get on and play with the next shiny thing!

Doing things for me, awesome, that works. Doing things that have an expectation from a third party, not so fun.

If you build something, sit with your users, listen, build community etc. I don't think that cheapens the final product.

The animation carries it, don't worry.

So many launches don't show what they are. This on the other hand - got it straight away from the animation.

Great job

How does that fit the YC W26?

You building something else and this scratches an itch?

That aside. I actually love this. Anything that helps with the "wtf did you just do?".

If I can still learn I will. If an agent can't reason about the changes made, then they are not good changes.