#034: Perplexity AI For Research (Web Crawling & Up-To-Date Sourcing)

In partnership with

Welcome to this week’s edition of the Architecture Insights newsletter. Artificial intelligence for architects, landscape architects, and designers.

AI deepfakes are getting so realistic that it's hard to tell what's real and what's fake. The most effective chatbot for research isn't ChatGPT, Claude, or Gemini - it's Perplexity.

This Week In AI

ChatGPT Search

OpenAI is set to unveil a new search feature for ChatGPT.

This new search feature will let ChatGPT tap into online sources to answer queries.

Certain versions might also include relevant visuals like diagrams or illustrated instructions alongside textual responses.

For designers, this could change how we gather information for our projects by giving us the ability to source from the most recent projects and designs.

Deep Fakes Are Improving

Deep fakes keep getting better, making it more difficult to distinguish between real and fake.

Check out a video of Reid Hoffman, an AI entrepreneur with his custom-made deep fake clone.


A tool for creating presentations with project information and extensive customization options to match your requirements for project presentations and slides.

The future of presentations, powered by AI

Gamma is a modern alternative to slides, powered by AI. Create beautiful and engaging presentations in minutes. Try it free today.

Perplexity AI

Perplexity is important in the world of large language models (LLMs). It may not be as advanced as ChatGPT or Google Gemini, but it can be better for some tasks, especially in research and sourcing the web.

One of the key advantages of Perplexity AI is its ability to access and analyze the web to scan for credible sources, including academic journals, industry publications, and reputable online resources.

An architect or landscape architect might ask Perplexity AI for the latest building code updates or recent changes in zoning laws for a specific region. Perplexity AI can source real-time information from the web, ensuring the architect receives the most current and accurate data.

For example, an architect could ask:

"Can you provide the latest building code updates for commercial buildings in New York City?"

Perplexity AI would be able to pull the most recent information from relevant sources, whereas ChatGPT might rely on its training data, which could be outdated.

How does Perplexity stay up to date?

  • Perplexity AI uses web crawlers to continuously scan and index websites, academic journals, news articles, and other online resources. This is a big benefit compared to ChatGPT, which usually doesn't give sources for its answers, especially in the free version.

  • When someone asks a question, Perplexity checks its stored information and searches the internet to find the best and most recent answers.

  • Perplexity applies various filters to the search results, prioritizing reputable sources. It can identify and exclude low-quality or unreliable sources.

  • Perplexit checks how trustworthy sources are by looking at things like the author's knowledge, the reputation of the publication, and whether there are citations or references.

  • When Perplexity shares its results, it lists the main sources it used. This helps users check the information and look into the sources more if they want to.

You can try using Perplexity here (this is not a sponsor).

Use pro features on the free plan by enabling the option at the bottom right of the prompt box.

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.

Did you enjoy this week's post?

Login or Subscribe to participate in polls.