The most valuable pieces of information an AI agent startup can gather is access to their customer's proprietary data and knowledge of their customers preferences (memory + self-learning).
Even as the cost of writing code goes to zero, those two pieces of information are non-commodities.
By my calculations 100k could get you 18 5090's + compute to host them, or 18 96gb Mac mini's. You can get a lot of context window and users out of that setup.
Instant gives you a database, but it also gives you a sync engine that you can use in the frontend. We included this instruction because you would ideally use this to build an app.
Right but it's not your responsibility to direct the UI. Your responsibility is backend services, possibly at a stretch, the architecture of apps as they relate to using those backend services, but it's most definitely not the aesthetics.
What if the app is headless and the LLM tries to stick a UI on it? What if the app is a TUI and the LLM gets stuck on terminal fonts? What if my UI aesthetic is grungy hackercore and the LLM tries to make it look like every other Tailwind website?
This criticism/feedback is less about what's written, and more about why it was deemed appropriate. You're getting direct input to the development process of your customer's products, and you're using that responsibility to... make pointless comments about design?
The UUID doesn’t actually affect the response. Every GET request still generates unique credentials each time, no matter what the value is that passes to /provision/<uuid>
We added it to help the app builders that do a lot of caching get unique responses. Turns out even if you set no-store cache headers, some app builders cache the pages. We tested this idea with those app builders and saw that they did generate uuids each time.
> Is this the kind of use case that is seen as valuable?
I think it could be. Consider an argument like this:
It's valuable to ask ChatGPT questions and receive text responses. Some of the responses are more valuable when they don't just return text, but some markup: bolding, adding visualizations etc. Why can't some responses be more valuable if they return little apps?
One place where I've wanted this myself are with using LLMs for long-running goals I have. For example, I do my blood work about once a year, and I use the results to make changes and track. For a long time I had a long chat thread with ChatGPT. Now I have a little app instead.
An extreme version of this starts to turn responses into more and more fully-fledged apps. I did an experiment recently with creating a personal finance app. I found customizing the app to my specific needs made it much more valuable to me then generic personal finance apps, which have much more effort put it, but aren't tailored to my needs [^1]
One place where a tool like GETadb can be helpful, is when you as a developer wanted to build a quick demonstration. For example one of co-founders Joe saw a tweet about how VCs were ranked. He pointed Instant to an agent, made a quick polling app, and got 600 votes [1].
We hope delightful experiences like that then prod hackers to dive deeper and use Instant for startups.
1. For the users table specifically, we have a default rule that says `"view": "auth.id == data.id"`. This way even if the the user (or AI) did not set access controls, user data is protected by default.
2. In the instructions file given to the agent (https://www.getadb.com/provision/new), we specifically mention permissions and how to push them. We found this prods the agent to push perms.
> It is highly unlikely that an AI agent startup becomes wealthy by creating the best harness for a particular use case.
If it's not the harness, what do you think is the thing that will differentiate AI agent startups? Is it mainly data, or something else?
reply