Impressive and full of great potential!
Congrats on shipping this.
Off topic question out of curiosity:
If we are builde a simpler visual "workflow" tool that allows users to drag and drop components on to a canvas, connect them, create brancing logic etc and configure properties of each components in a properties panel .... is there a good open source library/framework that we can add to say a React front end that has a lot of this UI already available? Thanks
We use react-flow which seems to be the go-to for any sort of node/canvas based UI at this point.
What’s the path to MS365 integration? Thats where all my work is
Working on it at the moment, would be interested in learning more about the actions/events you would need to make it useful.
Random but I love the name. I feel like we've entered into a new fun era of startup names. No more ___ly or ___ist etc. This era is generic word/noun + arbitrary numbers or letters after it.
I think ChatGPT really kicked that off, but maybe it was something else that inspired it?
Less normie/friendly and more technical sounding. So far, I'm a fan!
Partially inspired by WD-40 but more so the exorbitant price for anything workflow.com. The number did have some logic behind it: 8 letters in automate and 6 in no-code.
I thought it had to do with the 8086 dynasty of of Intel processors and the relation to tech and automation that computers have.
Ahh, I thought it meant the slang "86 it". As in it'll throw out your old workflow for a whole new paradigm.
We've heard this as well and also sometimes use it as explanation. Who knew "86" could make sense in so many ways.
Curious as to how this stacks up to some of the other AI copilots, I think Make and Zapier kinda have something similar?
Our AI goes much further than Zapier/Make in terms of how far it can get you towards a complete, ready-to-run workflow.
Make's copilot is pretty limited to generating an outline of the flow by selecting the right nodes but does not actually configure them. You still need to manually click into each one and set it up.
Zapier goes a bit further than Make, but it still leaves the workflow with a lot of configuration work that needs to be picked up by the user.
In both Make and Zapier, you really need to prompt the AI copilot in a very specific way to get good results. In our case, the AI is designed to use its business analyst/consultant mode to extract information so it can work from very general, unclear and ambiguous instructions to a clearly defined workflow/process to build.
The ability for our AI to edit the workflow at any time (including on top of your own manual changes) also means you can have a continuous iterative dialog/interaction with our AI copilot vs a once off interaction at the start. Both Make and Zapier's AI Copilots lack this or are very weak in being able to edit existing workflows reliably.
What exactly is "your AI"? From how you describe it, it's a GPT model with a "You're a business consultant" prompt.
I'm sorry to be rough, but from your description it just sounds like your AI somehow does a better job with prompts compared to Zapier & Make, which is highly subjective.
Besides that, this looks very cool and IMO is the future of interfacing AI automations in work environments
Valid point. At its core, our AI is indeed a LLM that is prompted to provide an output. A lot of the work however is in (1) prompting it in a way that allows it to actually understand the user instructions and current state of the workflow and (2) allow it to reliably output a response that acts as a set of instructions on what needs to be done within the platform e.g. add this, remove this, change this question text to this, write this code etc.
One example of what we had to do to achieve this was to develop an "intermediary language" defines how the current state of the workflow is represented to the AI and how the AI responds back - this needed to capture enough detail about the workflow without overwhelming it with too much context. We also developed techniques for structuring the prompting, with the process of building a workflow actually split into 3 stages: a pre-build planning stage, a build stage where the overall structure of the workflow is set, and then a build node stage where each individual node its configured. There is a bunch of other techniques we developed to get LLMs to be able to do what they current do, but these are just some examples of how it's a bit more than just a "You're a business consultant" prompt.
One thing I'd encourage people to do is test these co-pilots head-to-head on the same prompt. If you were to ask Zapier or Make to "build me a process for triaging customer complaints", I'd expect them to not get very far, perhaps an outline of some apps you could connect together to achieve it. If you asked our AI this same request, it would be able to deliver a complete workflow with fully configured forms, tables, branching logic, tasks etc
Slick UI, curious how practical the workflows actually are. My suspicion is that this is automating the part humans would want to do (designing the workflow), whereas most of the hours put into workflow automation is integration (90% of which is not going to be a clean REST API).
That said, maybe this would be really valuable to someone doing a greenfield project without needing to back into existing workflows. Either way, cool project.
Integrations are definitely the toughest part of the implementation. That being said, I'm pretty optimistic on (1) AI getting better at writing the code/REST API calls or making it a lot easier or (2) the sort of browser agents we've seen with Open AI Operator, Claude Computer Use etc get good enough to integrate via the UI layer vs the API level.
Some new users are encountering issues with the AI during onboarding - if you do encounter an error, you can always try out the AI again by just click the glowing purple button on the right of any workflow canvas! This seems to be due to some rate limit issues from the uptick in self-serve sign-ups and hopefully should be resolved soon.
You should add 2500 app integrations to Workflow86 via Pipedream Connect -- https://pipedream.com/connect
I find humor that a product like this exists.
Not because it isn’t useful (to be honest it looks decidedly useful as an API aggregator service) but the fact that one of its main selling points is for “AI”.
Yet, if we had AI, it would be able to build these integrations itself
Very interesting will definitely check it out!
are you using n8n for the workflow builder?
Nope, we built the workflow builder entirely ourselves, but I guess most workflow builders do end up looking very similar!
That strikes me as a surprising choice given the amount of prebuilt integrations with n8n
One factor in hindsight for doing this in-house was we did find out that AI can struggle with understanding and navigating existing workflow builders that were built and optimized for human usage and comprehension e.g. what nodes are available, the options that can set inside of those nodes and even how they are named had quite an impact on whether the AI could reliably form valid workflows on its own.
Not that surprising if you take n8n license into account. Its very prohibitive.
How is this better than Zapier?
Because we started with a focus on orchestrating forms and tasks, I'd say we're more suited for complex, long-running workflows that involve a lot of stop/start steps assigned to different teams (e.g. review and approvals) mixed with automation in between.
We actually integrate with Zapier i.e. you can trigger a workflow from Zapier, and we can trigger a zap from within a workflow.
While Zapier has also done some great work in the AI space, I'd also say our Ai builder goes a lot further in being able to fully set up a workflow and then continue to help users edit, change and refine them at any point. We're able to do this because a lot more of the moving parts are internal to Workflow86 (forms, tables, tasks etc), so the AI has more context and control over what it can do.
Looks like your product might be a perfect acquisition target for Zapier then ;)
Oh god, anything would be better than Zapier. They are so laden with legacy bloat; their UX is slow and cumbersome. A classic case of enshitification.