Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Launch HN: InspectMind (YC W24) – AI agent for reviewing construction drawings

news.ycombinator.com

Post reply on HN
Print view View original

41–50 of 59 posts

Re: Launch HN: InspectMind (YC W24) – AI agent for reviewing construction drawings

#41

Post by aakashprasad91 »

an_aparallel wrote: post #34
aakashprasad91 wrote: post #32

Earlier quoted context omitted.

Yes one of the biggest values of our system is reducing “noise.” Instead of surfacing 2,000 micro-clashes, we cluster findings into higher-order issues (e.g., “all conflicts caused by this duct run” or “all lighting mismatches tied to this dimming spec”). We’re not a BIM viewer yet, but we do map issues back to sheet locations, callouts, and detail references so teams can navigate directly to the real source of the p…

Sounds good, what is the typical workflow aggregating sheet sets in question for a certain phase? I assume user collates and drops for analysis?

Yes today users simply gather the sheets for whatever phase they want reviewed (DD, 80% CDs, 100% CDs, etc.), ZIP them or upload PDFs directly, and the system handles the rest. It auto-detects disciplines, reconstructs callout graphs, and runs checks across the full set. We're also adding integrations with ACC/Procore/Revit so sheet aggregation becomes automatic.

Re: Launch HN: InspectMind (YC W24) – AI agent for reviewing construction drawings

#43

Post by aakashprasad91 »

cannedbread wrote: post #42

When I upload my drawing set, how often should I expect it to hallucinate? And how much of the real stuff does it flag?

Hallucinations still happen occasionally, but we bias heavily toward high-confidence findings so noise stays low. On typical projects we surface a few hundred coordination issues that are real, observable conflicts across sheets rather than speculative checks. We’re actively improving precision by learning from every false positive customers flag. We show you the drawings, specs, etc. so you can verify it yourself not just trust the AI.

Re: Launch HN: InspectMind (YC W24) – AI agent for reviewing construction drawings

#44

Post by aakashprasad91 »

oscarmcdougall wrote: post #40
aakashprasad91 wrote: post #27

Earlier quoted context omitted.

We parse symbols using a mix of vector geometry, OCR, and learned detection for common architectural/MEP symbols. Cross-discipline checks are a big focus as we already flag mismatches between architectural, structural, and MEP sheets, and we’re expanding into deeper electrical/mechanical spec alignment next. Would love to hear which symbols matter most in your workflow so we can improve coverage.

We're in a similar space doing machine assisted lighting take offs for contractors in AU/NZ, with bespoke models trained for identifying & measuring luminaires on construction plans. Compliance is a space we've branched into recently. Would be super interested in seeing how you guys are currently approaching symbol detection.

Happy to swap notes. If you send a representative lighting plan set, we can run it and share how the detector clusters, resolves, and cross-references symbols across sheets. Always excited to compare approaches with teams solving adjacent problems.

Re: Launch HN: InspectMind (YC W24) – AI agent for reviewing construction drawings

#45

Post by shuangly »

cannedbread wrote: post #42

When I upload my drawing set, how often should I expect it to hallucinate? And how much of the real stuff does it flag?

We do extensive preprocessing to ensure AI receives accurate context, data, and documents for review, and we’re continuously refining this, so accuracy keeps improving every day. Right now the accuracy isn't super stable yet across projects, but we've had findings with > 90% accuracy results

Re: Launch HN: InspectMind (YC W24) – AI agent for reviewing construction drawings

#46

Post by pondemic »

I’m sure commissioning engineers would have a field day with this. Have you considered use cases on the larger owner’s side of things? As an owner’s rep I can definitely see value here at an SD and DD level, especially if the owner has a decently sized Facilities or commissioning team.

Re: Launch HN: InspectMind (YC W24) – AI agent for reviewing construction drawings

#47

Post by aakashprasad91 »

pondemic wrote: post #46

I’m sure commissioning engineers would have a field day with this. Have you considered use cases on the larger owner’s side of things? As an owner’s rep I can definitely see value here at an SD and DD level, especially if the owner has a decently sized Facilities or commissioning team.

Great point! Owner’s reps and commissioning teams are becoming one of the fastest-growing user groups for us. At SD/DD we can surface coordination risks early, highlight spec–drawing mismatches, and give owners a clearer picture of design completeness before things get locked in. If you’re open to it, we’d love to run a sample SD/DD set from your world and see what’s most useful.

Re: Launch HN: InspectMind (YC W24) – AI agent for reviewing construction drawings

#49

Post by djprice1 »

aakashprasad91 wrote: post #27
knollimar wrote: post #24

What kind of system to you have for parsing symbology? Do you check anything like cross discipline coordination (e.g. online searching specification data for parts on drawings like mechanical units and detecting mismatch with electrical spec), or it wholly within 1 trades code at a time? edit: there's info that answers this on the website. It seems limited to the common ones (e.g. elec vs arch), which makes sense.

We parse symbols using a mix of vector geometry, OCR, and learned detection for common architectural/MEP symbols. Cross-discipline checks are a big focus as we already flag mismatches between architectural, structural, and MEP sheets, and we’re expanding into deeper electrical/mechanical spec alignment next. Would love to hear which symbols matter most in your workflow so we can improve coverage.

What do you mean when you say "vector geometry"? Are you using the geometry extracted from PDFs directly? I'm curious how that interacts with the OCR and detection model portion of what you're doing

Re: Launch HN: InspectMind (YC W24) – AI agent for reviewing construction drawings

#50

Post by aakashprasad91 »

djprice1 wrote: post #49
aakashprasad91 wrote: post #27

Earlier quoted context omitted.

We parse symbols using a mix of vector geometry, OCR, and learned detection for common architectural/MEP symbols. Cross-discipline checks are a big focus as we already flag mismatches between architectural, structural, and MEP sheets, and we’re expanding into deeper electrical/mechanical spec alignment next. Would love to hear which symbols matter most in your workflow so we can improve coverage.

What do you mean when you say "vector geometry"? Are you using the geometry extracted from PDFs directly? I'm curious how that interacts with the OCR and detection model portion of what you're doing

Great question. By “vector geometry” we mean we’re using the underlying CAD-style vector data embedded in many PDFs (lines, arcs, polylines, hatches, etc.), not just raster images. We reconstruct objects and regions from that geometry, then fuse it with OCR (for annotations, tags, labels) and a detection model that operates on rendered tiles. The detector + OCR tells us what something is; the vector layer tells us exactly where and how it’s shaped so we can run dimension/clearance and cross-sheet checks reliably.
Post reply on HN