The easy version of AI for building code is a chatbot that reads the codebook and answers questions in plain language. It is fluent. It is fast. It is almost always wrong in the ways that matter.
The harder version is a system that surfaces issues with a citation a reviewer can verify. That is the system architects need.
Why the chatbot shape is wrong for the problem
Building code is not advisory. It is the legal basis a project is permitted against. An answer that paraphrases the code shifts the work of verification onto the person reading the answer — at a moment when they are designing, not auditing.
Summaries also hide their failure modes. A summary that is wrong by one occupancy class, one threshold, or one exception reads exactly the same as a summary that is right. The architect has no signal.
What a real citation looks like
For a flagged issue to be useful, the citation has to be specific enough that a reviewer can open the codebook and verify it without help. That means, at minimum:
- The adopted code edition (IBC 2021, CBC 2022, etc.)
- The chapter, section, and paragraph or table
- The specific element in the model the issue is tied to
- The values the system used to reach the conclusion
"Egress capacity is insufficient" is not a citation. "IBC 2021 Table 1004.5, applied to a Group B occupancy at 150 sf/occupant for the 2,400 sf assembly area shown on Level 02, requires 16 occupant capacity at this exit" is a citation.
The local amendment layer
Every jurisdiction adopts the model code with modifications. Sometimes a single section is struck. Sometimes a whole chapter is replaced. Sometimes a state amendment is overridden by a city amendment.
A useful citation has to surface both layers. The model code section that applies, and the local amendment — if any — that modifies it. Without that layering, the architect cannot tell whether they are looking at the rule that actually governs the project.
What this constraint rules out
Once "every issue has to cite a verifiable source" is a hard requirement, a lot of tempting shortcuts stop being acceptable — anything that paraphrases the code, blends it into a summary, or otherwise can't show its work against the source text.
The bar is simple to state and hard to meet: the adopted code is the source of truth, and every result has to trace back to it.
Auditability is the product
Architects do not want to be told they are out of compliance. They want to be able to confirm that a flagged issue is real, decide how to resolve it, and stand behind that decision with a stamped set.
That means every issue the system surfaces has to be defensible — to a colleague, to a client, to a plan reviewer. The citation is what makes that possible.
"The system told me" is not a defense. "Here is the section, here is the value, here is the element" is.
What a trustworthy result requires
For a flagged issue to be worth acting on, it has to:
- Point to the exact code section it came from, in the adopted edition
- Reflect the local amendments that actually apply to your project
- Show the values behind the conclusion, not just a pass or fail
- Stand on its own, without asking you to take our word for it
None of that comes for free from a model that answers questions in plain language. It's a high bar — and it's the one we hold every result to.
Where we landed
Kestrel is built to clear that bar. Every flagged issue comes back tied to the element that triggered it and cited to the code section that governs it — checked against the licensed code itself, not a summary of it. The result is something you can verify, not just trust.
We wrote about the underlying approach here: AI building code compliance in Revit →
If you want to see what cited issues look like on your own model: Schedule a demo →