|
|
|
Joined the wait list 1 week ago - any news on when it will open up or how fast you are taking new users?
|
|
|
|
Thanks for making this for us! Congrats on your big day
|
|
|
|
|
|
This is going to be an awesome way to optimize Zapier usage. I'm not a huge AI guy but love the idea of sprinkling a little on top of my existing zaps to make them even more useful! For example I have a zap right now that every time I react in slack with :todoist: it adds it to my TODO backlog. If I can use AI to read that thread and put a summary in there that'll make me more productive.
|
|
|
|
I'm the PM at Zapier for this and this is one of my personal favorite ways to use GPT-3 in Zapier. Linking you a template. Change the Trigger to New Reaction added. Set it to :todoist: and the user as yourself. Enjoy! Use this Template: https://zapier.com/webintent/create-zap?template=1173093
|
|
|
|
|
I would really love to hear a bit about Zapier's pursuit towards innovation. There are quite a few workflows automation platform out there. It is now an entire industry. With nocode being more and more popular, there is a lot of "Alternative to Zapier platforms". This makes me wonder, is innovation in no code workflow automation platform limited to just new API services? Or is there possibility to innovate in a new way? Some of Zapier's competitors have integrated programming language interface, spreadsheet element etc. As the OG workflow automation platform, what does innovation mean to Zapier beyond hosting an API service?
|
|
|
|
Replying as the PM on the NLA API. But you might want to check out some of the other tools Zapier is building that go beyond being an API connector. Also keep an eye out for more AI stuff soon! https://zapier.com/early-access
|
|
|
|
Related: I've been seeing a ton of news/references to LangChain recently. My own team is working closely with LLMs, and my non-technical cofounder is pushing hard for us to adopt LangChain as one of our core tools. So I spent a couple days diving into the LangChain codebase and I just don't understand why I would use LangChain. It feels to me like almost all of the LangChain codebase is dedicated to solving non-complex problems or interfacing with dozens on dozens of third-party APIs. All that said, the LangChain team looks solid, they've definitely been shipping code fast, tons of people have committed to the ecosystem, they raised a bunch of money, and I'm a huge believer in just going with standards. Has anyone here worked through this same dilemma, or a similar one, and could maybe help me with how I should be thinking about it?
|
|
|
|
I’m only looking at it for the first time but it looks like a framework to me. And that promises all the usual benefits (and drawbacks) of any framework. - learning the framework is a one-time cost that pays dividends over multiple projects. Subsequent products can be built by only implementing the domain-specific stuff above the framework. - presumably the stuff solved by the framework is non-trivial. It might be “obvious” (in hindsight) but chances are the framework designer has thought about it much more than we want to. - (theoretical) the framework will outlive any single generation of LLM. This is a fast-moving space and learning a new API or model every few months isn’t going to be fun. Hopefully the framework will adapt and adopters can transition to new models using one framework they already know. Only the third really applies to an existing project adopting the framework. Is that applicable in your case?
|
|
|
|
Congrats on the launch. Looks useful for certain types of users. I can imagine it now: > Hey Zapier, generate a new Keygen license for ACME Co. and send the license key to them via email using Postmark. Send me a copy of the email as well. Lastly, mail them a new customer postcard. Going to share this with a few customers today.
|
|
|
|
I wonder if they fixed replying to Gmail threads. Last time I tried, without the NLP layer, it failed to do anything but create new threads.
|
|
|
|
We just added a "Gmail: Create Draft Reply" action and by default the NLA API will auto-guess the appropriate thread. Share feedback if you see this not working as expected as it's new!
|
|
|
|
Congratulations Zapier team! I've been an active Zapier user for the past 6 or so years, and my teams have adopted it for various simple integration projects. I'm excited to see what more we can do with Zapier's new Natural Language Actions.
|
|
|
|
Congrats on the launch y'all, this is very neat! This was obviously a big effort. I'm excited to see how the introduction of AI will change the way integrations are built, maintained, and well, integrated. Cheers!
|
|
|
|
This would be really “fun” to scale with all the synchronous work going on. You guys definitely picked one of the hardest businesses to be in given the ungodly number of service providers you interface with! Very impressive.
|
|
|
|
Super cool. Applied to keep building a calendar that lets you Spend Time from a time budget.
|
|
|
|
Man, that would be great if we can add a step to summarize an article before posting it to social media
|
|
|
|
|
|
You could accomplish this with the existing chatGPT integration
|
|
|