To me it was Django that made python a choice of language to develop on. On top of it , not dealing with pointers of c++ made it much simpler to use.

Grateful for Meta to release models and give the GPU access for free, it has been great for experimenting without the thinking overhead of paying too much for inference. Thank you Zuck.

https://www.produceapp.ai/ For 2 If you ever want to chat about 2, i would love to say hello

Impressive and a good mission startup! How did you get workday, peoplesoft etc. to give the data to you? I assume all these companies do not like to share data, since as someone else also pointed out that each of these system of records are adding AI capabilities and bundling them.

Appreciate the kind words. You’re right that the big SIS and ERP vendors are building their own AI features, but at the end of the day institutions own their data and expect interoperability across systems. Workday, PeopleSoft, and similar systems all provide APIs or integration layers that schools already use for reporting and warehousing.

Where those systems are more closed, we work with the institution to find creative but still sanctioned paths such as through their integration hub or data warehouse. That way we are not asking the vendor for special access, just making better use of the plumbing that is already there.

Would be great to understand topics from family via AI (givem all the interviews are fed there) that they can’t discuss face to face

Disco it , currently Nordstrom catalog is LLM searchable

https://www.ddisco.com/

Pretty slick. I recorded a session for ordering from a restaurant website, and it did repeat the entire workflow. It had some issues with a modal popped up but all in all well done! We have been trying to robotify the task of ordering from restaurant for our clients and seems like your solution can work well for us. I am guessing that you want your users to use Autotab browser, what is use for API?

Thanks! We think of the browser as an authoring tool where you create, test and refine skills.

After you've done that, the API is great for cases where you want to incorporate Autotab into a larger data flow or product.

For instance, say Company A has taught Autotab to migrate their customers' data - so their customers just see a sync button in the Company A product, which kicks off a Autotab run via API. Same for restaurant booking, if you'd want that to happen programatically.

Understood! How does it work if we have several different restaurants to order from, do I need to record each ordering session and create skills for each restaurant or it can infer on its own given the task to order from a restaurant. Secondly, any docs or samples to see how to integrate this with your API?

Depends on how different the flows are for different restaurants. If they're just different names but use the same booking system you'd typically use an input and have Autotab find the correct restaurant first. If they're totally different booking systems you can try the instruct (open ended agentic) step but my guess is that will be too slow and unreliable for now, so you'd probably want to record different skills for each.

Docs are here with sample code: https://docs.autotab.com/api-reference

Is the API also charged based on runtime? And I'm assuming that workflow happens in the cloud? What if it's behind a login? What if that login requires 2FA?

Yep exactly. Authentication is primarily handled with session data, so passwords never leave your device, but we also support setting secrets.

Here is more info on auth and security: https://docs.autotab.com/manual/security

For 2FA, different users take different approaches. Everything from teaching Autotab to pull auth codes from their email, to setting intervention requests at the top of their skills, to enterprise integrations that we support with SSO and dedicated machine accounts.

Also for the modal popup - this is the kind of issue that goes away in run mode because Autotab will escalate to bigger models to self-heal.

If the modal pops up frequently you can also record an click to dismiss it and make that click optional so Autotab knows to move on if the modal does not pop up sometimes.

Amazing work! I have been working on robotifying operation task for my company - a robot hand and a vision that can complete a task on the monitor just like humans do. Have been toying with openAI vision model to get the mouse coordinates but it’s slow and does not return the correct coordinates always (probably due to LLM not understanding geometry)

Anyhow , looking forward to try your approach with mediapipe. Thanks for the write up and demo, inspirational.

I think weekday may be better!

Prototyping :

- Financial credit building for children via parent

- a better Siri (but many companies in this space is demotivating)

- a Capitol Hill Club, kind of like a country club for people, parents, kids to relax after work and which is not a restaurant

> - a better Siri (but many companies in this space is demotivating)

Don't be discouraged, there is so much room for improvement, and we had a better system than Siri (regarding general ability to answer open domain questions) back in 2004 (SMS-based, with a view to eventually incorporate speech recognition).

I have not seen a player that does this really well, and the need is unquestionable (despite the VCs that told me in 2004 that the mobile Internet won't be a thing because "if it will be possible, it will be so expensive that no-one uses it").