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

51–59 of 59 posts

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

#51

Post by aakashprasad91 »

zodo123 wrote: post #48

How does your system do with hand-drawn plans from an old-school architect? Is reliable OCR and line reading dependent on CAD output plans?

We do best on CAD-originated PDFs where we can use the underlying vector data, but we can run on scanned/hand-drawn sets too. In that case we rely more on image-based detection + OCR (no clean vector layer), so accuracy depends on scan quality, contrast, and how consistent the annotations are. We’ve had success on some older/detail-heavy scans, but it’s definitely a harder mode. If you have a representative “old-school” set, we’d love to run it and show you where it works well vs where it struggles.

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

#52

Post by djprice1 »

aakashprasad91 wrote: post #50
djprice1 wrote: post #49

Earlier quoted context omitted.

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 ex…

Woah! What determines if something is an object at that vector level? I've done some light PDF investigations before and the whole PDF spec is super intimidating. Seems insane that you can understand which things are objects in the actual drawing at the PDF vector level

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

#53

Post by sparselogic »

aakashprasad91 wrote: post #8
sparselogic wrote: post #7

This is fun to see. Some of my family are Division 10 contractors: their GCs love them because they spot design coordination and code issues early and keep the project from getting derailed. Bringing that to the entire project is a serious lifesaver.

Totally! Division 10 and specialty trades are often the first to see coordination issues show up in the field. We’re trying to bring that same early-warning benefit across the entire drawing set so errors never make it to construction. Would love to run a real project from your family’s world if they’re open to it!

One of them is interested. What’s the best way to contact you?

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

#54

Post by aakashprasad91 »

sparselogic wrote: post #53
aakashprasad91 wrote: post #8

Earlier quoted context omitted.

Totally! Division 10 and specialty trades are often the first to see coordination issues show up in the field. We’re trying to bring that same early-warning benefit across the entire drawing set so errors never make it to construction. Would love to run a real project from your family’s world if they’re open to it!

One of them is interested. What’s the best way to contact you?

Awesome — thank you! Easiest is email: aakash@inspectmind.ai or they can book a demo call on our website or upload plans directly on website. If they can share (1) a representative drawing/spec set (or a small sample) + (2) what trade/Division they focus on, we can run it and send back findings with sheet refs.

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

#55

Post by knollimar »

djprice1 wrote: post #52
aakashprasad91 wrote: post #50

Earlier quoted context omitted.

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 ex…

Woah! What determines if something is an object at that vector level? I've done some light PDF investigations before and the whole PDF spec is super intimidating. Seems insane that you can understand which things are objects in the actual drawing at the PDF vector level

Mamy of the drawings in pdf space have some layer data from CAD/revit attached to them that might make it easier to cluster objects

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

#56

Post by sparselogic »

aakashprasad91 wrote: post #54
sparselogic wrote: post #53

Earlier quoted context omitted.

One of them is interested. What’s the best way to contact you?

Awesome — thank you! Easiest is email: aakash@inspectmind.ai or they can book a demo call on our website or upload plans directly on website. If they can share (1) a representative drawing/spec set (or a small sample) + (2) what trade/Division they focus on, we can run it and send back findings with sheet refs.

Two emails are in your inbox. :)

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

#57

Post by aakashprasad91 »

sparselogic wrote: post #56
aakashprasad91 wrote: post #54

Earlier quoted context omitted.

Awesome — thank you! Easiest is email: aakash@inspectmind.ai or they can book a demo call on our website or upload plans directly on website. If they can share (1) a representative drawing/spec set (or a small sample) + (2) what trade/Division they focus on, we can run it and send back findings with sheet refs.

Two emails are in your inbox. :)

Starting on their first project! Thank you!

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

#58

Post by aakashprasad91 »

knollimar wrote: post #55
djprice1 wrote: post #52

Earlier quoted context omitted.

Woah! What determines if something is an object at that vector level? I've done some light PDF investigations before and the whole PDF spec is super intimidating. Seems insane that you can understand which things are objects in the actual drawing at the PDF vector level

Mamy of the drawings in pdf space have some layer data from CAD/revit attached to them that might make it easier to cluster objects

Yep, exactly, when layer data survives the PDF export, it’s a huge help. We use it as a weak signal for clustering and object grouping, but never rely on it fully since it’s often inconsistent or stripped. When it’s there, accuracy and speed both improve noticeably.

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

#59

Post by aakashprasad91 »

knollimar wrote: post #28
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.

I do electrical so parsing lighting is often a big issue. (Subcontractor) One big issue Ive had is drafters use the same symbol for different things per person. One person's GFCi is another's switched receptacle. People use the specialty putlet symbol sometimes very precisely and others not. Often accompanied by an annotation (e.g. 6-15R). Dimmers being ambiguous is huge; avoiding dimming type mismatches is basically…

This is exactly the hard part symbols aren’t enough when each drafter overloads them, so we lean on the annotation + schedule context (fixture tags, notes like “DIM,” control zones, panel/ckt callouts, and control intents) to disambiguate.
Post reply on HN