[brianbreslin]

This is a neat concept. I have no clue what this costs to setup, since its likely got a big setup time expense (training each site), but looks cool.

Are there other areas you've noticed that benefit from computer vision to compare base vs deviations?

[karims]

Great point, so key here given the variability in manufacturing processes is to have a plug & play setup. That's why we are working on getting our setup time down to just a few hours, through focusing on unsupervised model adaptation.

Re other areas: Same concept can be applied to anywhere where fast reaction times to deviations are essential and deviations are visually distinct. Think loading docs, where you want to make sure that cargo is loaded in time or machine assembly where you want to avoid delays. I think the list of areas where such an approach would add value is quite long.

[bluelightning2k]

I'd suggest not doing this.

What you're doing is not novel. You have a much better chance if you focus e.g. food and beverage.

There's many reasons but your setup will go smoother, GTM will be easier and you will get higher NPS. You will also have the opportunity to develop novel aspects.

[karims]

We are indeed focusing - my comments regarding other areas where my personal thoughts on the above question and not Cerrion's strategy.

[brianbreslin]

I was going to say this seems best as a packaged solution + consulting/setup fee. I could see this working in fast-food assembly stations as well, but may have more variance with human element.

Also could add on an analysis component of "study my flow and quantify potential jam points".

[karims]

We are more in the mode of "deploy cerrion at your most critical production vantage points and we tell you when, why and where deviations happen". This mode doesn't require any consulting, because that every manufacturer knows their critical points and our tech doesn't need manual customization. We will focus on processes where this is always applicable and consulting is not needed to be able to achieve fast growth.

The analysis of quantifying potential jams points and surfacing targeted improvement areas is smth we are already working on given that this can be done automatically in the customers dashboard by running some correlation analysis on our detections