We actually started off using the AutoGPT framework. There are a ton of remnants of that (tasks, steps) but we found the framework extremely limiting as we wanted to expand and do more complex things
For example, we're currently using a multi agent architecture where we have micro agents run to analyze SVGs, fill out dynamic autocompletes. This would have been really hard.
Frameworks like langchain are good for early prototyping, but it's too restricting when you want to push the limits
most people who run into limits w/ frameworks tend to mention they want more control over the prompt. Were there other dimensions that autogpt/other frameworks made difficult?
we started this last year. Back then, autogpt was more of a prototypical framework -- I'm sure it's improved dramatically since then. We ran into too many issues while developing with it (how do you run tasks effectively? How do you track artifacts related to previous executions?)
For example, we're currently using a multi agent architecture where we have micro agents run to analyze SVGs, fill out dynamic autocompletes. This would have been really hard.
Frameworks like langchain are good for early prototyping, but it's too restricting when you want to push the limits