UI vs. API. vs. UAI
joshbeckman.org
UI vs. API. vs. UAI
1–10 of 54 posts
Re: UI vs. API. vs. UAI
#2This is already true for just UI vs. API. It’s incredible that we weren’t willing to put the effort into building good APIs, documentation, and code for our fellow programmers, but we are willing to do it for AI.
Re: UI vs. API. vs. UAI
#3if you want your app to be automated wouldn't you just publish your api and make that readily available? I understand the need for agentic UI navigation but obviously an api is still easier and less intensive right. The problem is that it isn't always available, and there ui agents can circumvent that. But you want to embrace the automation of your app so.. just work on your API? You can put an invisible node in your UI to tell agents to stop wasting compute and use the api.
Re: UI vs. API. vs. UAI
#4This is already true for just UI vs. API. It’s incredible that we weren’t willing to put the effort into building good APIs, documentation, and code for our fellow programmers, but we are willing to do it for AI.
I think this can kinda be explained by the fact that agentic AI more or less has to be given documentation in order to be useful, whereas other humans working with you can just talk to you if they need something. There's a lack of incentive in the human direction (and in a business setting that means priority goes to other stuff, unfortunately).
In theory AI can talk to you too but with current interfaces that's quite painful (and LLMs are notoriously bad at admitting they need help).
Re: UI vs. API. vs. UAI
#5https://mcpui.dev/ is worth checking out, really nice project; get the tools to bring dynamic ui to the agents.
Re: UI vs. API. vs. UAI
#6This is already true for just UI vs. API. It’s incredible that we weren’t willing to put the effort into building good APIs, documentation, and code for our fellow programmers, but we are willing to do it for AI.
I think this can kinda be explained by the fact that agentic AI more or less has to be given documentation in order to be useful, whereas other humans working with you can just talk to you if they need something. There's a lack of incentive in the human direction (and in a business setting that means priority goes to other stuff, unfortunately). In theory AI can talk to you too but with current interfaces that's quit…
I also think it makes a difference that an AI agent can read the docs very quickly, and don't typically care about formatting and other presentation-level things that humans have to care about, whereas a human isn't going to read it all, and may read very little of it. I've been at places where we invested substantial time documenting things, only to have it be glanced at maybe a couple of times before becoming outdated.
The idea of writing docs for AI (but not humans) does feel a little reflexively gross, but as Spock would say, it does seem logical
Re: UI vs. API. vs. UAI
#7I really vehemently disagree with the 'feedforward, tolerance, feedback' pattern.
Protocols and standards like HTML built around "be liberal with what you accept" have turned out to be a real nightmare. Best-guessing the intent of your caller is a path to subtle bugs and behavior that's difficult to reason about.
If the LLM isn't doing a good job calling your api, then make the LLM get smarter or rebuild the api, don't make the API looser.
Re: UI vs. API. vs. UAI
#8This is already true for just UI vs. API. It’s incredible that we weren’t willing to put the effort into building good APIs, documentation, and code for our fellow programmers, but we are willing to do it for AI.
We are only willing to have the Llm generate it for AI. Don’t worry people are writing and editing less.
And all those tenets of building good APIs, documentation, and code are opposite the incentive of building enshittified APIs, documentation, and code.
Re: UI vs. API. vs. UAI
#9Separating presentation layer from business logic has always been a best practice
Re: UI vs. API. vs. UAI
#10I really vehemently disagree with the 'feedforward, tolerance, feedback' pattern. Protocols and standards like HTML built around "be liberal with what you accept" have turned out to be a real nightmare. Best-guessing the intent of your caller is a path to subtle bugs and behavior that's difficult to reason about. If the LLM isn't doing a good job calling your api, then make the LLM get smarter or rebuild the api, don…
> Protocols and standards like HTML built around "be liberal with what you accept" have turned out to be a real nightmare.
This feels a bit like the setup to the “But you have heard of me” joke in Pirates of the Caribbean [2003].