{"id":445,"date":"2024-02-19T23:39:48","date_gmt":"2024-02-20T06:39:48","guid":{"rendered":"https:\/\/blogs.ubc.ca\/axonometric\/?page_id=445"},"modified":"2024-02-26T21:42:17","modified_gmt":"2024-02-27T04:42:17","slug":"ai-dialogue-for-site-analysis","status":"publish","type":"page","link":"https:\/\/blogs.ubc.ca\/axonometric\/ai-dialogue-for-site-analysis\/","title":{"rendered":"AI Dialogue for Site Analysis"},"content":{"rendered":"

AI Dialogue for Site Analysis<\/b>: <\/span>Use a chatbot to develop your site analysis.<\/span><\/i><\/p>\n

Sign up for an account with an LLM chatbot, such as ChatGPT, Google Gemini, Microsoft Copilot, or Perplexity AI. In most cases, a limited free trial is available.<\/span><\/p>\n

\"\"<\/a><\/p>\n

 <\/p>\n

Think of a few questions you have about your site, based on your in-person observations and the landscape elements you have drawn in your CUBE. For example, if you noticed water pooling on your site, you might want to query probable reasons for pooling water in an urban setting.<\/span><\/p>\n

Find the prompt-entry text box. Here, input one question at a time. Chatbots understand \u2018natural language\u2019 prompts, so phrase questions how you would ask them of a person. You can add context to a multi-sentence prompt to refine your question. If the chatbot doesn\u2019t understand your question, try rephrasing it.<\/span><\/p>\n

For example, you could ask:<\/span><\/p>\n

Why might water be pooling in an urban park?<\/i><\/strong><\/p>\n

\"\"<\/a><\/p>\n

 <\/p>\n

Depending on how you ask the question, the chatbot will give different answers. Try asking your question in a few different ways, such as:<\/span><\/p>\n

Give all possible reasons for pooling water in a park.<\/i><\/strong><\/p>\n

\"\"<\/a><\/p>\n

I noticed water pooling near a large building in an urban park. What are some reasons for water pooling in this context? Could it have something to do with the building?<\/i><\/strong><\/p>\n

\"\"<\/a><\/i><\/span><\/p>\n

 <\/p>\n

Follow-up with further questions and <\/span>clarifications<\/span><\/i>. As you learn more about your site, identify one or two topics of interest for further exploration. For example, you may want to explore the soil composition or groundwater conditions of your site:<\/span><\/p>\n

What about the water table? Could groundwater be an issue?<\/i><\/strong><\/p>\n

\"\"<\/a><\/p>\n

What might a high water table mean for soil composition on this site?<\/i><\/strong><\/p>\n

\"\"<\/a><\/p>\n

 <\/p>\n

Next, try asking the chatbot for design suggestions related to your topic of interest:<\/span><\/p>\n

What are some design interventions that could ameliorate pooling water on an urban site in Vancouver?<\/i><\/strong><\/p>\n

\"\"<\/a><\/p>\n

What are some plants that would thrive in saturated soils and help infiltrate water on the site?<\/i><\/strong><\/p>\n

\"\"<\/a><\/p>\n

My site is in Vancouver. Which of these plants would thrive in this climate?<\/i><\/strong><\/p>\n

\"\"<\/a><\/p>\n

What are some specific plants (native to British Columbia) that would thrive in these saturated soils?<\/i><\/strong><\/p>\n

\"\"<\/a><\/p>\n

 <\/p>\n

IMPORTANT: <\/strong>Now you should verify the accuracy of what you’ve learned from your AI dialogue. Chatbots compile information from a wide variety of online sources, many of which may not be accurate. LLMs are also known to \u2018hallucinate\u2019, or make-up information.\u00a0<\/span><\/p>\n

Use a conventional search engine (i..e, Google) to confirm any information you would like to carry forward in your site analysis or design response. Make sure to check what you learned from the chatbot against reputable sources, such as academic journals, books, and other publications.<\/span><\/p>\n

Some chatbots, like Perplexity AI, attach sources to answers. If they are provided, follow these links to determine if the information was drawn from a reputable source. With Perplexity AI Pro you can also specify the type of source used to generate answers, allowing you to limit information to only academic sources, for example.<\/span><\/p>\n","protected":false},"excerpt":{"rendered":"

AI Dialogue for Site Analysis: Use a chatbot to develop your site analysis. Sign up for an account with an LLM chatbot, such as ChatGPT, Google Gemini, Microsoft Copilot, or Perplexity AI. In most cases, a limited free trial is available.   Think of a few questions you have about your site, based on your … <\/p>\n

Continue reading “AI Dialogue for Site Analysis”<\/span><\/a><\/p>\n","protected":false},"author":93064,"featured_media":0,"parent":0,"menu_order":0,"comment_status":"closed","ping_status":"closed","template":"","meta":{"footnotes":""},"class_list":["post-445","page","type-page","status-publish","hentry"],"_links":{"self":[{"href":"https:\/\/blogs.ubc.ca\/axonometric\/wp-json\/wp\/v2\/pages\/445","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/blogs.ubc.ca\/axonometric\/wp-json\/wp\/v2\/pages"}],"about":[{"href":"https:\/\/blogs.ubc.ca\/axonometric\/wp-json\/wp\/v2\/types\/page"}],"author":[{"embeddable":true,"href":"https:\/\/blogs.ubc.ca\/axonometric\/wp-json\/wp\/v2\/users\/93064"}],"replies":[{"embeddable":true,"href":"https:\/\/blogs.ubc.ca\/axonometric\/wp-json\/wp\/v2\/comments?post=445"}],"version-history":[{"count":9,"href":"https:\/\/blogs.ubc.ca\/axonometric\/wp-json\/wp\/v2\/pages\/445\/revisions"}],"predecessor-version":[{"id":492,"href":"https:\/\/blogs.ubc.ca\/axonometric\/wp-json\/wp\/v2\/pages\/445\/revisions\/492"}],"wp:attachment":[{"href":"https:\/\/blogs.ubc.ca\/axonometric\/wp-json\/wp\/v2\/media?parent=445"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}