Can you elaborate on what you mean by “it’s almost assumed..”? I’m actively working on datasheet parsing at scale at Zenode.ai, and I haven’t read anything specifically about this…

I sloppily glommed a lot together there.

The pdf parsing was certainly the least mature capability of those that I mentioned. Got decent results with the pdf parsing tool that ships with Claude (desktop) but ultimately wrote a subagent definition to help with pdf parsing. I found myself sticking to vendors with the most parseable (or ideally html) datasheets formats TI, AD, Microchip all fine - but I did learn to love Wurth Elektronik. I looked into doing a custom RAG solution for this.. docling etc. to smooth over things like tables split between pages, Figure reading. Ultimately found their team to be responsive on discord and figured they have every incentive to solve this for me by the next time I find time for a hobby electronics project.

Generally the llms were awesome at discovering the chips I needed (with a few hallucinations promptly uncovered - like a TI mux chip which didn’t exist in the automotive grade designation for that package) without a doubt shortened my search and design development time by some large factor. I remember some AWESOME solo distance driving where i voice chatted with GPT 5x doing thinks like picking the right RS485 driver ic and microcontroller pairing without needed to wade through datasheets

The python is less in need of explanation I’m sure

This is basically just a vent about all the sh!t i've dealt with over the years as a EE

Thank you! Yeah, missing pricing and availability is a tough one, but I'm really hoping we'll be able to get it from the distributors in return to funneling better traffic towards their sites...

We've actually heard this from a few industries, there's definitely a lot of different vertical AI opportunities here! Right now we're very focused on just doing electronic components, but maybe someday!

Yeah, this was actually a nightmare . We had to create "canonicals", which ended up being a mix of regex, machine learning and good old manual human labor. Fortunately, we could usually rely on the datasheet as the 'source of truth', but even that approach failed when faced with the overwhelming amount of part data we were shifting through.

From all of our customer interviews, almost everyone used Digikey and the occasional manufacturer website to find parts.

Because of that, we're seeing many people put the parameters they're looking for directly into the search. After a few searches, it starts to be clear that you can add more information directly into the search, so queries get a little more complex.

We're getting ready to add features to the AI to help you (interactively) navigate the range of available parts to narrow down your choices and understand what's available when you don't know where to look or what parameters to use. You should be able to ask 'I need to convert a parallel RGB display bus into MIPI' and the AI will show you different families of parts that could do that.

Well, that's super annoying, we definitely don't want that, thanks for finding and letting us know! We'll have it fixed shortly.

Digikey's parametrics were the best in industry prior to ours, but they were still really painful to use because of the strings. But to even get to the parametrics, you first have to know in advance the category and subcategory names of the part you're looking for. There are over 3000 different categories, so even once you're pretty good, you're always asking yourself "is what i'm looking for in the logic category or the amplifier category". With Zenode, all this is handled using natural language! And we did a huge overhaul on the parametrics, we turned the strings into structured values and built modern filters that are just waaay easier to use.

Octopart is a bit of a different beast from us. They're crushing the pricing and availability data, which is actually hard to get (a LOT of business development to get access to the realtime values from the distributors themselves). Plus they have a really massive catalog, definitely broader than ours, but they don't have the depth (i.e. the detailed spec and documentation data) that we do because we went to the manufacturer websites to obtain that.

We're learning a lot here, since this always happened AFTER we handed over the BOM. It certainly seems like a pain, particularly when a supplier ends up being a critical bottleneck (always late, overcharging, etc). The number one requested feature from these folks is a way to validate an alternate component, something they can use for themselves BEFORE passing it over to us design engineers for approval (heard some pretty spicy takes on doing this, apparently working with EE's isn't always sunshine and rainbows...)

Yeah, Moat's are tricky in the age of AI. We think there's always room for a standalone interface in this niche sector, given the sheer amount of data that needs to get presented (with no room for hallucinations). But beyond the data curation (which is actually quite hard) and the custom UI, there's also all the tuning data to optimize for the workflows that come next, like Alternates, schematic awareness, etc.

But yes, OpenAI continues to be the 800lb gorilla 'boogeyman' crushing startups with every new update. Our goal is to remain cockroaches until we find solid distribution!

Thanks for the candid response. I'd expect that because you're not one of the AI giants that you'd be able to work with the different suppliers more easily - licensing deals and even embedded tools in their websites. As far as I can tell, your business model doesn't rely on assimilating as much info as possible, so you're better positioned to work within suppliers' IP and sales pipelines.

That's the hope, but thus far we've been heads down building, and haven't had much time to chat with those folks.