Show HN: Magic Loops – Combine LLMs and code to create simple automations • Hacker News Board

Re: Show HN: Magic Loops – Combine LLMs and code to create simple automations

#51

Post by jumploops » Sat, Aug 05, 2023, 8:23 AM UTC

yu3zhou4 wrote: post #35

This is great. Please consider low cost tier for non-business users, I think many HNers would be willing to pay for such automations

Thanks. The biggest spend is definitely from GPT-4 and the scrapers, so we're exploring a "bring your own" keys approach for those that don't want to run it locally but keep costs down.

Re: Show HN: Magic Loops – Combine LLMs and code to create simple automations

#52

Post by jumploops » Sat, Aug 05, 2023, 8:26 AM UTC

royibernthal wrote: post #43

jumploops wrote: post #30

Earlier quoted context omitted.

Our goal with Magic Loops was to leverage a LLM-first approach to programming, allowing more people to write code that does useful things. It turns out that when you write simple programs, they often resemble what you'd find on Zapier or IFTTT :)

Wouldn’t it be possible to leverage Zapier for their integrations instead of trying to imitate that?

Definitely! Because it's just code at the end of the day, as soon as our code-runners have internet access you can integrate to your heart's content.

Re: Show HN: Magic Loops – Combine LLMs and code to create simple automations

#53

Post by vermaat » Wed, Aug 09, 2023, 9:49 AM UTC

Tiberium wrote: post #25

This looks really cool! I really think an idea of a proper UI tool to chain different tools together is nice. https://flowiseai.com/ seems to be the most similar, but it's quite a bit more technical, and doesn't seem to be focused on doing the whole thing by itself - rather, you can create chains that can then be used through APIs. I really hope you open-source this :)

Nice work. I'm trying to build something similar, yet different: FlowFlow.AI: Automate your core business workflows by defining step-by-step tasks and follow up actions for the AI agent to execute. - The AI agent decides the appropriate next step in the workflow based on one of the predefined conditions. - Keeps the AI in control within the boundaries of your complex workflows. - Use the FlowFlow API or Python/JS packages to interact with the workflows in your code. FlowFlow.AI is almost ready for the beta launch. :-)