I think the agent part is deciding how to navigate the web on its own and when it is convinced (and you haven't told it specifically deterministically) it found what it wanted, to come back and work with your prompts. You can't really logic code this into a workflow.
I don't work in prompt engineering but my partner does and she tells me numerous need for agents in cases where you want some technology which goes and seeks things on the live web and then comes back and you want to make sense of that found data with the LLM and pre-written prompts where you use that data as variables, and then possibly go back into the web if the task remains unsolved.
If anyone paying the right price to access a product, and no underlying technology, making it "open", isn't most of the world's technology open? Isn't Apple really OpenApple? Isn't Oracle really OpenOracle? Apple probably puts out more open-source tech than OpenAI.
Does the word mean much anymore, then? Is it nothing more than a sentiment then?
Perhaps OpenAI should have renamed itself to "AI for all" or something when they adopted the capped-profit model. Perhaps they should've returned donor funds and turned fully for-profit too. Perhaps that was a genuine resolution and pivot, which every org should be able to allowed to do.
Genuine question, I run a nonprofit whose name starts with "open". But we do explicitly bring closed source work to be more openly licensed, without necessarily making the technology open-source.
Btw, a very easy big win for you would be to port the side styles/interactions panel of WebStudio into this. And by port I mean extracting the code to make a common open-source library with the correct license and putting it in Puck.
This is just so fantastic, I have been looking for something like this for the open-source edtech app builder Flow (https://github.com/opencurriculum/flow) for the past year! Talked to the WebStudio guy and did so much research, but nothing was just right. This feels JUST. RIGHT.
I am so grateful for your comment because I did not know about your company and now I have been reading all your content and watching the videos and drooling on what you have put together. I am so mightily impressed and intrigued!
Excellent point. When I think of a foray into construction, I plan to use all software off-the-shelf and focus my process improvements entirely on-field.
Can we stop putting any of these product ideas on pedestals, as if they were acts of technological genius? They are all incremental interesting improvements, often thought of around the same years with unique insights, but not some revolutionary inventions no one has tried to build before. They are what they are because of their execution.
I have been following the Ubuntu homepage for about 15 years, and it's so interesting how they went from prominently promoting every CTA around downloading the desktop version, to now, where I had to spend 5 minutes trying to find a link on their site to the ubuntu.com/desktop site.