[HN Gopher] Launch HN: Bild AI (YC W25) - Understand Constructio...
___________________________________________________________________
Launch HN: Bild AI (YC W25) - Understand Construction Blueprints
Using AI
Hi HN! We're Roop and Puneet, the founders of Bild AI
(https://www.bild.ai). Bild AI uses machine learning to read
construction blueprints and extract detailed material quantity and
cost estimates. Here's our demo: https://youtu.be/vBDl7Mh7iEc The
problem we're tackling is the sheer manual effort that goes into
generating material quantities and cost estimates from blueprints
today. Contractors and suppliers spend countless hours doing
takeoffs by drawing on blueprints by hand - it's tedious, error-
prone, and costs the global industry $30B a year. A single mistake
can lead to thousands in losses on a project. My co-founder Puneet
experienced this firsthand as he was building hundreds of houses in
Canada. Meanwhile, my background is in applied ML - I started at
Google at 19, then Waymo where I built perception models for self-
driving cars. Puneet and I met at Hack for Social Impact where we
built our first _very_ narrow-scoped prototype. Since then we've
expanded our scope slowly, with a laser-focus on accuracy. Our
approach is to use a suite of specialized machine learning models
for specific blueprint comprehension tasks, rather than a single
end-to-end model. For example, we've developed computer vision
models that are highly accurate at detecting and measuring floor
areas, or identifying and counting framing elements like studs and
doors. By composing these expert sub-models, we can achieve high
accuracy on the overall takeoff. This is somewhat analogous to the
approach we took at Waymo for self-driving perception - having an
array of dedicated models for tasks like lane detection, traffic
light classification etc. It's a very different paradigm than the
big-data end-to-end models like what Tesla uses - unfortunately we
just don't have enough data yet. We're working with some early
customers like flooring suppliers to help automate their estimating
workflows. But we see a huge opportunity to expand this "AI that
understands blueprints" approach across all trades. Would love to
get the HN community's thoughts and feedback! Construction is an
industry I think is really ripe for applying cutting-edge ML
techniques. If you have experience in this domain as a builder,
architect, estimator, supplier etc. I'd love to hear about your
workflow and pain points. Also if you're a researcher or engineer
excited about applying state-of-the-art techniques to real-world
problems in underserved industries, definitely reach out! We're
currently live with customers but are only able to serve a subset
of trades accurately right now. Head to https://www.bild.ai/upload
if you want to try uploading a blueprint and we can talk about your
use-case. I truly believe we can solve blueprint understanding with
AI, and there seem to be a huge number of applications. I'll be
here all day to chat and answer questions!
Author : rooppal
Score : 92 points
Date : 2025-02-27 17:30 UTC (1 days ago)
| ev9 wrote:
| Seems like an interesting application of AI. Going to be obvious
| to many, in hindsight. Having run a business in the trades, I
| used to receive 5-10 emails a day from companies offering
| estimation services. Clearly there is a need in the market.
|
| It looks like your launch is opening this up to the general
| public - why not niche down to GCs? Maybe the launch is focused
| on simply gathering more blueprint data to feed your models?
| rooppal wrote:
| Our focus is currently on servicing suppliers and GCs. Our
| models would need labels to train, so we have to source our own
| data.
| FloorEgg wrote:
| Curious why you're going off of blueprints instead of BIM?
|
| The benefit of estimating quantities and cost cycles in with pre-
| con and business development, the artifacts during the pre-con
| design phase tend to be different than the takeoff artifacts
| which are often transformed through BIM.
|
| Did you learn something to the contrary? Or are you purposely
| targeting smaller firms and projects that don't use Bim and maybe
| won't for a long time?
| rooppal wrote:
| I really wish BIM took off more, unfortunately most suppliers
| and GCs are still using blueprints (but at least have moved off
| paper).
| rjsw wrote:
| As a developer of STEP, I wish BIM was used less.
| rafamvc wrote:
| What's step?
| rjsw wrote:
| The ISO 10303 family of standards [1].
|
| [1] https://en.wikipedia.org/wiki/ISO_10303
| salynchnew wrote:
| I was wondering what the training dataset looked like, and I'm
| very surprised that they're not using BIM data... although
| after living with an architect for 20 years, I think there's a
| joke in here somewhere about contractors and planning.
| szvsw wrote:
| Even if projects use BIM internally it's still completely
| possible that the final deliverables are all PDFs/drawings/etc
| generated from BIM/internal models for contractual/liability
| reasons etc.
| Enginerrrd wrote:
| Yeah this is almost like a solution to the wrong problem.
| Designers often start with the information in an easily
| extractable form, then it gets sort of compressed in a way into
| blueprints / plans to communicate it, and then re-extracted for
| takeoffs.
|
| BIM and other standardization is really the correct answer to
| this problem. This is a stop gap to cover for when/if that ever
| gets widely adopted.
| nicpottier wrote:
| Who is your market? In my area takeoffs are done by lumber yards,
| it's just a service they provide in order to win the business. So
| you are going to be selling B2B into a market that is very slow
| and resistant to change. I imagine many are using some software
| for their process but I've never seen it.
|
| On the other side, architects are using Revit more and more and
| takeoffs like square footage of flooring are accurate and take no
| time at all. That's another industry slow to change and that used
| to take more effort so many architects aren't providing that
| information to their clients, but technically there's nothing
| preventing it. There's a bit more hand waving when it comes to
| calculating number of studs etc, but that is pretty
| straightforward as well.
|
| Source: I'm funemployed as a drafter for a local architect after
| 25 years in software.
| rooppal wrote:
| We've seen that suppliers do a ton of bidding and cost
| estimation, and are keen to be accurate (estimate too high and
| they lose to competitors). GCs and suppliers don't want to be
| too low because that potentially costs them tens of thousands
| of dollars.
| patrickhogan1 wrote:
| I love the idea you guys are doing. I also think your name
| should have takeoff in it.
|
| As a side point - sometimes the shady lumberyards do bid too
| low on purpose to win business. Then later have the
| contractor submit a change order. This often hurts their
| reputation unless the contractor is in on it to win a bid.
| The supplier doesn't tend to lose money though as the bid is
| for the quantity of materials.
|
| You could turn this into a selling point. As in, helping a
| contractor or competing supplier verify the takeoff.
| chrisgarand wrote:
| Hey Patrick, this is rare, it does happen, but usually
| (almost always) it's that something was missed in the
| takeoff, the updated plan wasn't submitted to the yard, or
| the drawings were missing elements.
|
| I agree with your point, having a second, impartial source
| is important to confirm the ballpark.
| chrisgarand wrote:
| We do supplying to contractors, and do takeoffs for single
| family homes. Not tracked, one off's for framing material.
| You mentioned your co-founder has built tract homes so my
| words might not apply to your target customer.
|
| Here are things to consider:
|
| Experienced builders don't care about the takeoffs on a big
| picture basis, the takeoffs are usually wrong, even if
| perfectly done. In our experience half of drawings we
| receive, are heavily revised by the order is approved
| (heavily revised meaning over 10% has changed). EWP,
| structural metal need to be accurate but framing lumber, and
| sheet good can be off on counts at the lift quantity (+-1
| lift for an average house).
|
| Suppliers aren't responsible for the takeoff so the amount
| the quote is negligible (see drawing revisions, and trades
| can misallocate the materials - This can't be reasonably
| traced). Over? The customer ends up paying less, under? The
| customer pays more. This has been universal where I am
| (Ontario, Canada).
|
| A large minority of plans are missing key elements (like
| sheer walls), pointing out, and showing these differences
| would be a big value add for the consumer (contractors using
| the materials) by the supplier.
|
| Good customers understand that lumber is a commodity, a lower
| price this week can flip next week, and they'll contact their
| preferred vendor about the differences.
|
| There's always a preferred vendor.
|
| Not great customers will shoot drawing off to multiple
| suppliers, causing them all to do the same takeoff, wasting
| time, and money, only to deal with the same issues above.
| They'll still go back to their preferred vendor to get the
| lowest price.
|
| Summary of the above is: EWP, and structural metal are key
| items because they rarely change, framing lumber, and
| sheathing requirements change all the time. What you're
| looking at is helping suppliers capture the bad customers
| (which are often the biggest, to be clear), but saving
| suppliers the time handling them is great. Also, accuracy,
| and pricing isn't that important (with caveats).
|
| This isn't a statistically significant sample size, consider
| it anecdotal.
| serjester wrote:
| I love this, it seems like 90% of the YC AI startups are geared
| towards selling to devs. There's so much value to be had finding
| where AI is relevant in the broader parts of the economy,
| especially something like construction.
| johanssen wrote:
| Correction: A single estimating mistake can lead to MILLIONS in
| losses, the bankruptcy of the contractor, and years of
| litigation... lol!
|
| Estimators miss things ALL THE TIME. It's the subject of
| seemingly endless in-house arguments between PMs and Estimators:)
| harmmonica wrote:
| I feel like you must've put this somewhere, but where are you
| getting the cost information from? If I upload a blueprint and
| you tell me I need "x 2x4's at a cost of $y each totaling $z" for
| my project where is the y coming from? Can I tell you a specific
| supplier and then you'll "scrape" the cost data? Or maybe I'm
| misunderstanding what you're doing here.
|
| I'm asking because even though I am (mostly) technically
| illiterate I have asked both ChatGPT and Claude to help me build
| a scraper for construction material costs, from the suppliers we
| use, that can be updated in realtime or at least monthly. Haven't
| done anything with those instructions yet, but I would love
| nothing more than to use a tool that we could feed a blueprint
| into and then would tell me, with "laser-focus accuracy" <smile>
| how many x's the project would need and the costs. Even better
| yet if it could compare costs from suppliers and guide us to the
| lowest-cost supplier.
|
| Edit: oh, while you're thinking of replying, how high fidelity do
| the blueprints need to be? Again, I'm sure you specify somewhere,
| but too lazy to find it. How far along the spectrum from "drawn
| on a napkin" to "fully standardized" do you accept?
| rooppal wrote:
| Thanks for such a detailed question! We're focused on material
| quantity estimates right now. We're using pretty generic
| averages for costing as our primary users (suppliers) have a
| way better finger on the pulse of the market and typically
| change the unit price anyways. We'll work on better cost
| accuracy though, and are looking to integrate with RSMeans or
| building our own scrapers.
|
| For the second question, it really is most accurate on "fully
| standardized" blueprints due to our training distribution. Will
| work on improving that as well!
| harmmonica wrote:
| I realize you're opening yourself up to criticism if you
| answer this truthfully, but since suppliers are your primary
| user (and therefore _paying customers_ I assume?) your pitch
| is "supplier, you can do more with less (or no!) people when
| specifying material quantities, and in fractions of a second
| as opposed to the minutes/hours it takes today!" So,
| ultimately, if the suppliers fully trusted your solution they
| would need zero personnel determining quantities? And since
| your solution's annual licensing cost would likely be a
| fraction of the price of even a single individual that'd be
| pretty compelling to the supplier.
|
| Best of luck with the business (and with getting to know the
| corp dev people at Autodesk/Procore/etc.--sorry, couldn't
| help myself!).
| disgruntledphd2 wrote:
| > f the suppliers fully trusted your solution they would
| need zero personnel determining quantities?
|
| You'd still need people to check what actually got
| installed, so that you can bill for it. Like, there's only
| so much you can determine off the plans.
|
| And what happens if (when) the plans are wrong or
| impractical?
|
| My Dad worked in construction for his career, and I did
| briefly, and there's generally a lot of stuff that needs to
| be figured out on site due to physical or logistical
| constraints.
|
| Sounds like this is just for homebuilding though, which is
| a much easier problem.
| szvsw wrote:
| It seems like, with sufficient users entering data (including
| previous sales/purchases if desired), you could begin to
| train models to take into account local/regional factors etc.
| do you have any long term plans to collect user data in such
| a manner?
|
| Separately, it seems like it would be incredibly useful to
| use your models in various embodied carbon estimation tooling
| and other decarbonization research streams. Have you thought
| about partnering with any academic researchers on this? If
| you are interested, let me know, as I can definitely connect
| you with a bunch of researchers who would be interested!
| rooppal wrote:
| We don't really have plans on using user-data to train our
| models, since it's too much of a chicken-and-egg problem.
| Carbon estimating is something we had some clients talk
| about -- it uses the same material quantity estimation
| we're already doing, and is something we're really
| interested in (my heart is in impact-driven work). Would
| love the connections!
| DanKamau wrote:
| Oh hey welcome to the space. I'm the founder of
| https://www.sketchdeck.ai/. We started working on the same
| problem a couple of years ago. Took us longer than I would like
| to admit.
|
| What's crazy about this is that the AI revolution is going nuts.
| We've started with Steel and customers who would traditionally
| bid on paper are now jumping straight to AI takeoffs. The impact
| is real.
|
| One customer recently told us that he was able to bid on $200M
| more than he would have been able to otherwise:
| https://www.linkedin.com/feed/update/urn:li:activity:7300899....
| That's a couple of million in revenue that they would have worked
| away from because of capacity constraints.
| anonu wrote:
| Then you can bid out the materials buying too. This could save
| homeowners tons of money rather than let a GC manage it.
| bittermandel wrote:
| Congratulations to the launch! Funny how two separate companies
| launch a product in the same space within a short period of time.
| AI-BOB, https://www.aibob.io/, got a lot of attention during
| TechArenan in Stockholm last week.
| pontifier wrote:
| Very excited for the day that you reverse the process and can
| generate blueprints and changes on demand.
| rooppal wrote:
| I think that's well within the realm of possibility :)
| xrendan wrote:
| I love the Blueprint Understanding.
|
| One thing I've been thinking about is if you could use a model
| like this as the first pass for permitters (Like a GitHub Actions
| CI/CD) who review blueprints.
|
| Many developers use the regulatory side of various engineering
| approval processes as a quality control check which costs money
| and time for the regulator who is tasked with enforcing a
| standard.
|
| It would also be good to speed up the workflow for developers
| saying hey, this thing looks weird did you really mean to do
| this?
|
| And then further on, you could add a way to check it for
| constructability. My framer friends often get annoyed at whatever
| engineer because the way the structure is designed is materially
| inefficient or hard to construct.
| rooppal wrote:
| Absolutely! That's our end-goal, to remove the painful back-
| and-forth of permitting. Once you solve blueprint
| understanding, the possibilities are enormous, from spell-check
| to material efficiencies, etc.
| djsamseng wrote:
| Awesome! This is a huge opportunity to help a lot of people
| (clients, subcontractors and builders). A lot of money and time
| is wasted by the current inefficiencies. We gave takeoff
| construction plan parsing a go in 2022-2023 but couldn't get the
| AI part to work well enough (and still haven't been able to even
| with the latest ViT/ CLIP models). There was a lot of interest
| though!
|
| - You're right, data is very hard to come by. I'm curious, how do
| you plan to get around this? Outsourcing human labeling? We found
| it to be a very difficult task.
|
| - The subcontractors and local construction companies we talked
| to were overwhelming excited about the idea.
|
| - It's entire people's jobs to get this done and done correctly.
| They sit on site holding the pdfs in their hands, manually
| counting and calculating. You bet a lot of mistakes occur. They
| would absolutely love to have a digital assistant for this.
|
| - Some of them (especially managers and owners) are quite
| technical and are using software such as BlueBeam and other CAD
| software to make these calculations. It's quite manual currently,
| but gives great insight into a better solution. This led us to
| having the user manually select the symbol they wanted counted
| (which ML struggled to get right). Just getting the part counts
| (and highlighting them in the pdf) was a huge help!
|
| - Impressive you got square footage calculations correct! In our
| experience, there was way too much variation between architects
| (and multistep dimension labeling) which made it hard (even for
| humans) to get right. How has your model generalized OOD thus
| far?
|
| - Are you planning to integrate voice? Many of the subcontractors
| we worked with are very low tech. They usually talk with their
| clients in person, on the phone, or maybe text. But they don't
| use email or their smart phones for much.
|
| I will be following your work! I have friends who would love to
| use this once it passes the human threshold.
| rooppal wrote:
| I think parsing a whole blueprint with monolithic models is
| really difficult, but the constrained object detection/semantic
| segmentation problems are significantly more tractable. You can
| chain those CV models with VLMs to do things like get scale
| right. I'm always interested in novel HCI paradigms like voice!
| pkondle wrote:
| Interesting idea. Can i know how accurate or precise is your
| outcome. From a tech perspective, can you take more about how it
| works if you can?
| fzysingularity wrote:
| Congrats on the launch! What kind of computer vision models do
| you use under the hood?
| BrandiATMuhkuh wrote:
| Congratulations on the launch. This is really cool, and useful.
|
| Coincidentally, yesterday I had a client meeting and they ask for
| exactly that. I'm working as lead developer for
| https://howie.systems and we are building a co-pilot (knowledge
| platform) for the AEC industry.
|
| Would love to have a talk. Your product could save us lot's of
| work!
| rooppal wrote:
| Amazing, I saw you already connected with my cofounder over
| chat, looking forward to it!
| BrandiATMuhkuh wrote:
| Haha. Yes. Though that might be quicker :)
| realitysballs wrote:
| It's interesting space to build a solution. The need for quantity
| take offs of a 2D PDF drawing that is most likely built in BIM
| software is mostly driven by contract structure.
|
| If owners/developers understood this they could create contract
| structures that incentivize more fluid data collaboration aka the
| quantity take offs automatically generate as you are designing.
|
| Pragmatically though in the current AEC landscape there is still
| a need for 2D QTO, nice work
___________________________________________________________________
(page generated 2025-02-28 23:02 UTC)