# LLMs vs BV360 Pre-Flight

A generic AI chatbot is useful for drafting emails and summarizing a published code page you paste in, but it does not reliably read CAD dimension strings from a plan-set PDF and it does not hold the adopted amendments for each suburb.

Pre-Flight runs the same vision and language models, but binds them to a specific AHJ code library and a verify step so the output is cited, not confident-sounding.

| Capability | Generic chatbot | Pre-Flight |
| --- | --- | --- |
| Reads CAD dimension strings | Unreliable | Vision on cover + site, then you confirm |
| Which code | Whatever it remembers | Adopted library for the city you pick |
| Output | Prose | Findings with section citations |

## Worked example

Illustrative: a Skokie R-1 addition proposes a 2.75 ft side yard. A generic chatbot may recite a generic model-code setback that does not apply. Pre-Flight checks the proposed yard against the Village of Skokie R-1 standard (two side yards, neither less than 6 ft) and returns a flag with the section citation, so you know before you file.

Pre-Flight is not a permit, not legal advice, and not a substitute for the authority having jurisdiction. The city still decides.