<p>Agentic product is nice to have if im new to it, but for simple products I&#x27;m familiar with, having to put my thought into words is way more annoying than typing in a couple numbers in a UI. I always thought &quot;agent with tools&quot; is just a new version of UI which is a info delivery method.<p>But on a second thought, most people in a company is essentially &quot;agent with tools&quot;, so maybe it&#x27;s already pretty amazing

<p>Many of us use LLMs to generate code, tools and other artifacts without agents.

<p>Brex&#x27;s CEO said this and I understand where he comes from, but is there a place for end to end workflows in LLM based applications? At the end of the day I agree that cutting edge software should be fully usable by agents, but I can&#x27;t decide if every product should be an agent. I personally hate the UX of most agentic applications. I have this fantasy of future products where I can simply enter input X and get output Y without having to give feedback on every little thing. Of course when you&#x27;re designing something it needs to be a process, but what if I can tell my phone to &quot;buy dinner&quot; and it just does it without bothering me at every step? What if it was just good enough? I think a conversable agent is necessary as long as the application is unsure of the accuracy of the output, but I wonder if the UX of LLM applications could be more like a rich person fixing their car, like here is my situation, just do what you need to do and don&#x27;t bother me.

Is "An agent with tools" the only valid LLM application?

Comments

mermadicsolutio

cheevly