I'll bite. I'm currently building a new home based on plans of my own design, literally taking a lunch break now from hanging electrical gangboxes.
Do you have a background in homebuilding? Or have you ever built anything before?
Visualizing the design is one thing, but the feasibility must be considered -- and often vetted through engineer(s) -- from the initial design phase. And even then, despite the best planning attempts, inevitably there will be some issues that need to be addressed 'on-the-ground' during construction.
I think you may be onto something, and I believe LLM models could be capable of accounting for e.g. code restrictions, structural considerations, MEP conflicts, etc. Most of the 'knowledge' homebuilders accumulate is trainable and repeatable. And- at least in the US- most of it has been codified/standardized in the IRC. But still there are tons of little caveats & gotchas to consider. Maybe those details could be addressed directly in your system prompts?
Also curious: what kind of "other files" does Drafted export "for the rest of the pre-construction process"? IDK to what extent you've used any existing home design software, but Home Designer/Chief Architect are capable of creating a (detailed) BOM for the entire build, down to every member of framing lumber. If the user chooses to enter price information, they can also provide cost estimates. A seemingly obvious AI-assisted improvement would be gathering price data automatically- say from the Lowe's or similar Big Box Hardware nearest to the user's location. And ideally keeping it updated as lumber & other materials fluctuate in cost.
To me a really capable AI design software could also be capable of:
- Basic electrical load calculations
- HVAC/ Schedule D [ductwork] design
- Structural considerations- e.g., recommending a joist plan: type/size/direction/spacing of floor joists + validating against IRC and/or joist manufacturer load tables
- and a whole lot more
I have a number of other ideas in case you're interested. Feel free to send an email (in profile).
PS- are you familiar with BIM software (like AutoDesk Revvit)? There a lot of 3D modeling capabilities you could borrow that go way beyond floor plans and aesthetic architectural considerations.
Google puts far too much stock into the "accuracy" of its Maps data.
Here's my fun story: in order to verify my dad's website with Google's 'My Business' service (now a defunct product?), they had to mail a physical postcard with PIN code to ensure the address was legitimate. Picking the mailing address was hooked into Maps/ Maps data; a "real" address had to be among their existing database of addresses.
Well, my dad lives in a somewhat-rural area outside St. Louis. His street is "Alt Road" -- named after the Alt family, German immigrants who started a large farm in the area 150+ years ago.
Yet Google Maps had the street listed as "Alternate Road". Clearly some data entry person presumed it must be an abbreviation and took liberty to 'correct' the apparent mistake.
So it was literally impossible to have a postcard mailed to his address on Alt Road. I had to have it sent to Alternate Road instead. I recognize, of course, the verification steps taken thereafter will have permanently corroborated what was bad data in first place. Now I'm part of the problem.
I'm guessing Maps will now forever have renamed the street. Should I alert the county to Dad's 'new' mailing address?
Also doing it in rural Missouri. I grew up & lived in the St. Louis area/ suburbs first 30 years of my life; that's where (most) family still resides.
I have a small agency and work independently from home. Currently have a sweet gig for a Global Fortune 500 corporation with offices all over the U.S. and around the world. Every day I collaborate with colleagues spread across North America, yet I still get to enjoy the beauty of the countryside. Occasionally I'm asked to travel into St. Louis (90 minutes) or Nashville or Cincinnati (6 hours each, respectively) for meetings.
Several years ago I "escaped" to a large wooded property just outside a small town with population around ~4500. Fortunately I also have a small college town 20 minutes away - home of the University of Missouri tech & engineering campus - with full-year population ~25k (it's also the county seat), where I can shop at Wal-Mart, Lowes, Staples, Kohl's, etc. In fact, there is also a brand new Starbucks + new development just opened with a Menard's, PetSmart, TJ Maxx and more.
So while I enjoy the privacy and peace of rural living, I also have a number of modern conveniences within easy reach. Also worth noting: my small town is fairly affluent, so there are nice restaurants (including a place with 20+ craft beers on tap), and we have a full-size grocery store.
Upsides of working rurally:
* Money goes significantly further. Not so much for typical everyday items and consumables, but especially because:
* Housing is VERY affordable.
* Property taxes are extraordinarily low. I have a 4000+ sq/ft home with 5BR and 3BA on 160 acres. Total annual real estate tax is less than $2k. Smaller home on 1/3 acre lot in STL suburbs was 2.5x that amount.
* Personal property tax and sales tax rates are also quite low. That makes it much more affordable to purchase/own vehicles, farm equipment, etc.
* Multiple, awesome farmer's markets every week -- 52 weeks/year -- where you find (inexpensive) produce, eggs, meat, dairy, baked goods, and you buy directly from the actual farmer/producer.
* Don't see any neighbors. Rarely hear them.
* True sense of ownership over your environment - no need to "keep up with Joneses" like you do in Suburbia
* Feeling of isolation. That's an upside for me, but won't apply universally of course.
Downsides:
* Maintaining a large property is a lot of work. A DIY mindset is helpful. So is a chainsaw.
* Poor cell service.
* Few/expensive internet choices. Currently using a 20Mbps satellite connection (which works just fine, including for realtime screensharing via Skype or WebEx) that costs $120/month. Earlier this year my telco line-carrier (CenturyLink) finally began offering DSL, so I plan to look into that -- cheaper but may be slower.
* Not much nightlife, few opportunities to socialize.
* No Whole Foods, Costco or Sam's Club. So I generally go into St. Louis once or twice a month to stock up.
If you're considering making the "escape" yourself, I would strongly consider the following:
* Road access. Rural properties differ significantly -- even within a small area -- based on the length & quality of roads you need to travel. Personally, my driveway connects to a _numbered_ state highway with hard pavement in good condition (maintenance and slow plowing are prioritized over smaller _lettered_ highways & county-maintained roads). Plus it takes only 10 minutes to get to the Interstate highway... a huge win. Compare that with some rural areas where you might either: A) travel a long distance on two-lane roads to reach the Interstate; and/or B) drive for miles on a gravel road just to hit pavement.
* Related to above: your driveway. In case of snow you'll probably need to plow yourself. If it's gravel, you'll need (or need to hire someone with) a tractor for periodic road maintenance/grading. Likely need to haul in & spread more gravel every few years.
* It's stark contrast from life in a metro area. Everywhere you look parking lots -- including at the golf course -- are filled with pickup trucks. I was previously accustomed to an abundance of luxury cars as far as the eye could see.
The number of private aircraft owners in the US (immediately addressable market) is around 300,000. Overall global market is somewhat larger, but not tremendously since aircraft ownership per capita is MUCH higher in the US than any other country.
On the downside, too, the market size is admittedly shrinking slowly. Private aviation is generally less popular than it was, say 15-25 years ago (likely the result of increasing costs and regulations).
There are upsides to the aviation market, though, that may help outweigh its size: A) upscale/luxury/wealthy market - costs for everything are staggeringly high, so premium pricing applies; and B) aircraft enthusiasts are typically technology-driven and likely to be early tech adopters.
In terms of applying the software to other markets, which may be larger, we've given this some thought as well. While car/truck owners (or fleets) might benefit from this type of application, there are existing software solutions aimed at solving the problems of roadgoing vehicles.
Likewise, aircraft are fundamentally different from a regulatory standpoint. Failing to perform periodic maintenance can be illegal - and lead to fines, censure or losing certifications/licenses altogether… yet nobody is going to be arrested if they fail to change the oil in their Toyota every 5k miles.
Plus, aircraft are somewhat unique in that records and scheduled maintenance are all based on # of hours (not on mileage as in the case of cars & trucks). I have heard suggestions, though, similar software might be applied to "heavy equipment" - like bulldozers and cranes - which also have hourly logs. Market penetration seems much easier for aircraft, though, since the aviation community is smaller, more consolidated and more tightly-knit.
Thanks for your feedback. Great point about signatures; yes - the signature of a certified Airframe & Powerplant ("A&P") mechanic is required for maintenance entries. We foresee implementing a feature for collecting, and validating, electronic signatures.
In terms of retroactive conversion, you're absolutely right most aircraft in service now are generally decades old - and are going to have historical paper records. We have considered several novel approaches that would allow aircraft owners to electronically archive their existing paper logbooks (and maintain historical records alongside the newer all-digital records for user convenience).
Do you have a background in homebuilding? Or have you ever built anything before?
Visualizing the design is one thing, but the feasibility must be considered -- and often vetted through engineer(s) -- from the initial design phase. And even then, despite the best planning attempts, inevitably there will be some issues that need to be addressed 'on-the-ground' during construction.
I think you may be onto something, and I believe LLM models could be capable of accounting for e.g. code restrictions, structural considerations, MEP conflicts, etc. Most of the 'knowledge' homebuilders accumulate is trainable and repeatable. And- at least in the US- most of it has been codified/standardized in the IRC. But still there are tons of little caveats & gotchas to consider. Maybe those details could be addressed directly in your system prompts?
Also curious: what kind of "other files" does Drafted export "for the rest of the pre-construction process"? IDK to what extent you've used any existing home design software, but Home Designer/Chief Architect are capable of creating a (detailed) BOM for the entire build, down to every member of framing lumber. If the user chooses to enter price information, they can also provide cost estimates. A seemingly obvious AI-assisted improvement would be gathering price data automatically- say from the Lowe's or similar Big Box Hardware nearest to the user's location. And ideally keeping it updated as lumber & other materials fluctuate in cost.
To me a really capable AI design software could also be capable of: - Basic electrical load calculations - HVAC/ Schedule D [ductwork] design - Structural considerations- e.g., recommending a joist plan: type/size/direction/spacing of floor joists + validating against IRC and/or joist manufacturer load tables - and a whole lot more
I have a number of other ideas in case you're interested. Feel free to send an email (in profile).
PS- are you familiar with BIM software (like AutoDesk Revvit)? There a lot of 3D modeling capabilities you could borrow that go way beyond floor plans and aesthetic architectural considerations.