The tool looks sick. I think the copilot vs black box approach is great. I found the demo to be enjoyable and satisfying to watch despite having no experience in the concrete estimation industry.

This is out of my wheelhouse but had a couple of thoughts. When you clicked P1, it found all of them. What happens if it doesn't? This would have been good to see in the video.

Also, I'm sure people familiar with these documents will have no trouble but was thinking it could be cool to do some effect to make references glow/be more noticeable at least temporarily when you are skipping around to them. Maybe some zoom controls too.

Anyways, good luck!

A friend works in construction and they have details of how much materials each part of a construction needs. Most of it comes directly from the (not sure the name) SW they use to calculate the structure/ draw the plans.

Looks like a useful tool but I don't know anything about construction.

Love the transparent AI helper implementation though. I feel like you don't even need to say it's AI because it's so helpful but not in your face but maybe that's what people are searching for.

If the AI miscalculates, and building crashes and people die - who is held responsible?

> We started this when Sahil took a construction management class and realized how the estimation workflows hadn't changed in decades

That's because it's been used in the construction industry for literally a couple of millennium (e.g. ancient rome) and it's a fairly well-understood material. The variations come in with the newer "exotics" rated above 5k psi that are more chemistry than aggregate, water, and portland cement.

Did your one class teach you that any non-parabolic concrete cross section is approximately 7% steel? And that the bidding issues with concrete are centered around the steel rebar/wwm/wwf installation and formwork/earthwork prior to pour?

[flagged]

[flagged]

[flagged]

[dead]

[dead]

I wonder if this approach to starting a vertical business the founders have 0 experience in has ever panned out. I know YC pushes the B2B SaaS angle as hard as possible, searching for "underserved" niches, but seems like if you don't have true industry experience, it can't possibly work out.

[flagged]

[dead]