011: AI For Code & Standard Compliance (Overview Of Existing Software)

Welcome to this week’s edition of Architecture Insights.

In the fast-paced and rapidly innovative industries of Architecture and Artificial Intelligence, it can be hard to keep up with where things are at. This week we will look at 3 use cases of AI in architecture.

As always, let’s first go over news related to AI in architecture from this week, the topic of the week, followed by resources for architects and designers to try out.

This past week

1. Amazon releases AI tools for business and work. (Read)

Summary: Amazon Web Services has launched Amazon Q, a specialized AI-powered assistant that can help businesses. It can use your company data and systems and the content is not used for training, which ensures data privacy. This is amazon's attempt to compete with Google and Microsoft with their AI assistants.

2. Stable Diffusion XL Turbo releases instant image generation. (Read)

Summary: Another competitor of Midjourney and DALL-E keeps improving. The feature could allow designers to start creating images as soon as they begin writing, resulting in quicker and more frequent idea generation.

Use Cases of AI in Architecture

Many designers have yet to explore AI tools, either because they lack interest or because they feel overwhelmed and don't know where to start.

Artificial Intelligence is becoming increasingly ubiquitous in our world, with its capabilities often going unnoticed. In this context, let's take a look at some of the use cases for AI in architecture.

1. Early stage concept design

Generating quick and (sometimes) accurate renderings using Artificial Intelligence is the most well-known area of AI use for most designers. Mid-journey and DALL-E are examples of tools that come into play here. These tools are great for generating design ideas, however, since we don't yet have full control over what the AI generates, the renderings may not always be entirely accurate.

Input your parameters and design criteria such as the style, size, location, and materials for better images. Iterate your images from there by re-prompting them.

For early-stage development we also see the use of tools like Maket become of great value for floor plan generation. The user needs to input their design criteria, and within seconds, they get access to more than 20 different layout variations to choose from.

2. Compliance with codes and standards

Iterating a design through numerous rounds of compliance checks can be a laborious and time-intensive task. During the design phase, it can often happen that we are unaware of certain codes and regulations that differ from one city or town to another.

There are tools like codecompliance.ai that are in development to create tools that assist architects, engineers, and anyone requiring approval to construct their projects.

It is as easy as uploading a plan and then having it analyzed by the software. As designers and architects, we know all too well how tedious and time-consuming the iterations and critiques of reviewers can be when we miss out on considering design standards or regulations.

3. Automating tasks

AI-driven automation tools seamlessly integrate into project workflows, offering architects time and focus away from tasks like meeting summaries, file transferring, and emails.

We can see with software like Zapier and Make that we can connect many of the weekly or daily tasks we complete to work with each other to save time.

Here is an example for architects and designers: Let us say you have just completed a long meeting with a client. You can use one software to save your meeting transcript and minutes like ClickUp.

By then integrating an automation tool you can take your notes without doing any additional work and have it create a Word document, and PDF of your notes (connecting to Word or Adobe), Summarizing your notes and send them in an email to all participants (connecting to your email service provider), and lastly storing that information into your files (connecting to SharePoint or notion). This can all be automated in one software without having to lift a finger after setting it up.

Resources & Tools

How to Use ChatGPT 4.0 for Free

To use ChatGPT 4.0, you need a premium plan that costs $20/month. However, there are ways to use it for free.

If you go to perplexity.ai and sign up for a free account then you can use ChatGPT 4.0 by toggling on “copilot” mode.

Two other tools are Bing Chat and Merlin, both offering free ways to use ChatGPT 4.0.

If you use ChatGPT for any of your architectural needs then these tools can offer similar if not better results if they are specifically trained on your given requests. I.e the AI chatbot software Jasper is nearly exactly the same as ChatGPT however it is geared more towards copywriters and marketers as it is trained on more data that improves its capabilities.

The catch with using these free versions is that they often come with a limit/cap on the questions you can ask per day or per hour.

Use AI to review legal documents such as proposals, safely. (Read)

AI Image of the week

Thank you for reading this week’s issue, check past issues here. Share this newsletter with colleagues, friends, or anyone interested in the combined world of architecture and artificial intelligence.

Feedback is always appreciated, let us know how we did by responding to this email.

Until next Friday,

A.I