HN Explorer

Show HN: Zenode – an AI-powered electronic component search engine (zenode.ai)

19 points by bbourn ↗ HN
TL;DR - My cofounder Collin and I built an AI version of Digi-Key to help PCB designers find and use parts, except with a way bigger catalog, modern refinement tools, and an AI that can actually read the damn datasheets for you.

*The problem*

Modern circuit board design is filled with absurdly tedious tasks, where one small mistake can brick a project and cost thousands. The worst (in our opinion) is reading datasheets, which eats up to 25% of the first part of any project: 1. First, you slog through catalogs to find viable parts, using search tools that are still stuck in the dark ages. There are ~80M unique components in today’s supply chain, yet the tools we have to look through them are just digitized versions of the same paper catalogs our grandparents got in the mail.

2. During the design, you spend a ton of time flipping between different 10-100-page PDFs for every component in every subcircuit, hoping like hell you don’t miss some tiny spec in a footnote somewhere that kills your design.

3. And god help you when the requirements inevitably change and now you have to figure out what subsystems are affected!

*What we built*

Zenode is an AI-powered electronics search engine that actually helps engineers find and understand components. Our core features: 1. Largest and Deepest Part Catalog → We have merged dozens of existing part catalogs and documents from major distributors and manufacturers

2. Discovery Search → natural language queries to quickly find categories, set filters, and rank results

3. Modern Parametric Filters → rebuilt from scratch to move off the string values pervasive in industry and build numeric ranges that actually work.

4. Interactive Documents → AI constrained to a single part’s datasheet/manuals. Ask a question, get the answer with a highlighted source for quick reference.

5. Deep Dive → search across dozens of parts simultaneously (“what’s the lowest-power accelerometer available?”) instead of slogging one by one.

*What we learned*

1. By far the hardest part of the last 2 years has been wrangling 3 TB of messy, inconsistent data into something usable. We had to teach the AI how to handle hand-drawn figures, normalize different unit variables and names that mean the same thing, and navigate conflicting information present between different datasheet versions of the same part. It’s been a nightmare

2. We originally built custom PDF parsers and AI extractors, which were best in class for ~3 months until generalized AI passed them. So we stopped reinventing wheels and doubled down on data quality instead.

3. The killer feature wasn’t the AI searching a single part, but what we heard repeatedly from users is that they want the AI to read across multiple parts, hence why we’ve launched deep dive!

*Where it’s strong*

- Speed: rips through a 1,000-page microcontroller datasheet in seconds.

- Breadth: 40M+ part sources unified into one catalog, and more than just datasheets, application notes, errata, etc.

- Comparisons: Deep Dive lets you ask across multiple parts, not just one at a time.

*Where it’s not*

- Pricing/availability: currently outdated (for now we expect folks to check existing aggregators like Octopart).

- Accuracy: good enough to match my mediocre skills; not yet at Collin's level, but we're starting tuning and this will improve rapidly!

*Try it*

It’s live today (zenode.ai). Sign up for a free account and If you put “Hacker News” in during signup in the “where did you hear about us” field, we’ll give you 1,000 bonus credits (once we finish building that, so sometime this week ).

*Feedback we’d love*

1. Should Deep Dive results auto-become filters you can refine further?

2. Do you want the ability to mark preferred parts / exclude others?

3. Is “Deep Dive on a BOM” (alt discovery + manufacturability checks on a list of known components from different categories) the killer feature?

17 comments

[ 3.7 ms ] story [ 38.9 ms ] thread
sofia44
Real neat! This tool could fill some tough gaps. This only works if there’s accuracy - is there a way to flag incorrect answers on the program?
rchaudhary
Congrats on launch. Two questions from a user perspective. 1) How do you handle spec changes across document revisions? 2) Can users export the analysis with links to the exact tables and figures in the PDFs?
benmathes
I see the value here. The problem isn't just the search; it's the trust. The biggest hurdle for Zenode won't be the tech, but convincing an engineer that your AI's summary of a footnote is accurate enough to risk a $10,000 board spin. That's a high bar.

I'd argue the core value isn't just a better search or a faster reader. It's about providing a verified, reliable source of truth. This brings up a key tension: you say the AI isn't yet at your co-founder's level of accuracy, but is that precisely the level of confidence required to replace an engineer's manual check? How do you close that gap? You've got the data, but the trust factor is a different threshold?

I.e. maybe you've built the tool to make the problem faster, but the real win would be a tool that makes the problem safer? The killer feature might not be more speed, but rather a confidence score on every AI-generated fact, with a clear path to the source document so an engineer can verify it. It’s not about avoiding the document entirely; it’s about having a better starting point and knowing exactly what to double-check.

GraemeWiltrout
This is awesome! Way better than DigiKey’s search.
ctstoner
Who we are We’re electrical engineers who have lived this pain firsthand for a decade; Brandon (OP) has designed a dozen boards, while I have built over 250 through production. Years ago we spun up a brand-new product line in two weeks to help salvage a $150M deal. That meant 18-hour days spent picking parts, doing CAD, paying $$$$$ for three-day prototypes and praying everything worked (one did blow up when we accidentally shorted 3 kV into a metal screw on the desk, we nearly died cause of a sleepy brainfart :dizzy_face:). Even from that working version, it took an additional four months of redesigns to get through certifications and into production. When ChatGPT shocked the world in ’22, we realized that the initial superpower of AI in electronics isn’t in generating designs (too risky — one mistake kills the board), but in digesting the endless unstructured documentation that plagues (benefits? :thinking_face:) our industry.
ccamrobertson
I'm toying around with a custom board and searching here is far better than shuffling through the old Digikey filters. Awesome!
KDunc
Congrats on your launch! What's your moat? The big AI players are getting better at reading datasheets and providing contextual guidance and info. It seems like it won't be long until ChatGPT and others will be able to do what your tool does. Thoughts?
sonaliv
How does this differentiate from Digi-Key’s parametric search or Octopart’s aggregation?
caromexia2
Congrats on the launch! How much of the component selection pain is actually on the supply chain side? Like, engineers pick parts, but then procurement has to source them without really understanding the technical tradeoffs. Have you talked to purchasing teams about this?
jkontulis
When normalizing specs across manufacturers, how do you handle cases where units aren’t directly comparable (e.g., different test conditions for “low power” claims, or different temperature reference points)? That’s often where human engineers end up second-guessing the catalog data.
jbryben
Congrats on the launch! Toyed around a bit with the site and seems really intuitive; though I used a few of your prebuilt suggestions: "A thermal fuse rated for 75°C and 10A, An optocoupler with 1.5kV isolation, and 5V LDO with 1A output" for example and all come back as not available/no parts available. Just FYI not sure if you want the autofilled suggestions to be the ones that don't produce the results.
alejandravl1901
This seems to be incredibly helpful, even if it's not 100% accurate. Then again, isn't that what chatGPT is for? How should I think about Zenode vs. a more generic AI search engine?
brunanovis1811
This looks like such a game-changer — congrats on the launch! I’m curious, what have you learned from how engineers were handling these challenges before, and how they’re starting to use Zenode now? It feels like those insights could really shape the next steps.
bgrubbj
This looks really promising. Datasheets are such a time sink and a common source of mistakes, so solving that pain point is huge. The Deep Dive feature especially stands out since searching across multiple parts at once feels like what engineers actually need. Curious how you’re thinking about pricing and availability since that seems like the missing piece to make this a daily driver.
Califishguy
Coming from the plant/facility management and process engineering side of things , the pain isn’t PCB parts but pumps, valves, blowers, sensors.

I'd be interested in the industrial-world application of being able to ask things like “which pumps are seawater-rated, 10 bar, 40k hr bearing life, share the same footprint, can run on the same VFD, have BSPT or BSPP threads?”

Do you see Zenode extending into that kind of industrial equipment/knowledge realm?

spasemanYC
Congrats on the launch! Deep Dive seems awesome. Curious how you deal with the fact that different vendors describe the same spec in different ways? That’s always been my biggest headache when trying to compare parts.