Asking AI about real estate zoning

AI and real estate

In my last few columns I have looked at artificial intelligence and it uses for real estate.

I had it look at pricing a home as well as market trend analysis (where prices etc. may be going). This time, I thought I would ask a simple question that anyone looking at buying a home might ask, “I am thinking of buying this house at (pick an address in B.C.). What do I need to know about the local regulation and zoning information.”

First I went to GROK (from X.com) and asked it. It came up with more than 1,600 words. Lots of great information.

It was careful to give me information but warned me to double check against the city’s zoning bylaws and, in this case, to use the Kelowna ap viewer to get it right. It also told me to look at the (city’s) Official Community Plan future land use designation, which outlines the city’s long-term vision for the property. It then gave a link to the map viewer.

This was the opening paragraph:

“To provide you with accurate information about local regulations and zoning for (the property), I’ll outline key details based on the City of Kelowna’s zoning bylaw and related resources. Since specific zoning details for an individual property require checking the city’s mapping tools or contacting the city directly, I’ll guide you through the process and highlight what you need to know, including general zoning regulations, how to verify the property’s zoning, and potential implications for your purchase.”

It followed up with several key things. Here is a condensed version.

1. Understanding Kelowna’s zoning bylaw

2. How to verify the zoning for the property

3. Likely zoning for the property

4. Key regulations to understand

5. Other regulatory considerations

6. Implications for buying the property

7. Steps to take before buying

8. Additional resources

It then gave me this summary. “To buy (the property) you need to verify its zoning (likely RU1, MF1, or MF4) using the Kelowna map viewer or by contacting the planning department. Key regulations include permitted uses (e.g., single-family, secondary suites, multi-family), setbacks, height, and density, influenced by the 2023 provincial legislation allowing up to four units in RU1 or six storeys in MF4 zones. Check for HCA status, archaeological restrictions, and compliance history to avoid surprises. Confirming these details ensures the property aligns with your plans, whether for living, renting, or developing, and protects your investment.

If you need help interpreting the map viewer results or want me to draft questions for the city, let me know.”

It actually looks pretty helpful and thorough. The best part, in my opinion, was all the links it provided so I could go and check to make sure all the information I had was up to date.

I also asked the question of ChatGPT. It came back with 285 words. ChatGPT gave me the zoning which was correct. It gave me permitted uses with a couple key regulations, as well as a link to review zoning bylaws. It also gave me some things to consider if I was planning on doing any renovations. It gave me a quick neighbourhood rundown and ended with this.

“For personalized advice or to discuss your specific plans for the property, consider reaching out to a local real estate professional or the City of Kelowna's planning department.”

I liked what I got from ChatGPT. It wasn’t as thorough (as Grok) but hit the high points and gave me places to look if I needed more.

Lastly, I asked Meta. It came back with 257 words about things I needed to do and questions I should ask. There were no links or any site specific information. It was very disappointing after what the other AIs came up with.

I am reasonably happy with the results of this test. Grok was thorough and ChatGPT did a good job with resources and links to dig deeper.

I do want to mention that if you are using AI to help, it is permissible and advisable to ask follow-up and clarifying questions. I would not necessarily book a contractor based on its answers but I would feel comfortable using its information and taking out my measuring tape to see what size of a mud room I can build on the front of my house without going past the required setback. After that I would call the city before I start digging to put in a foundation. Digging is hard. When I can get one of these AIs to work a shovel, that will make me happy.

I will give a point to AI this week. It wasn’t a big win but it was fast and convenient.

Score: AI-1 Humans-2

If you have suggestions for other real estate-related articles, please email me at [email protected]

This article is written by or on behalf of an outsourced columnist and does not necessarily reflect the views of Castanet.

Putting AI to the test with real estate pricing

AI pricing homes for sale

When the market needs insight, not just input

AI in real estate

In my last column, I wrote about how artificial intelligence was going to do lots of great things and make buying and selling real-estate a breeze.

For this column, I asked AI to do a market trend analysis of the Kelowna B.C. real estate market.

First up was Grok. It came up with about 1,200 words, which I then asked it to summarize to 150 words. This is what it said:

“The Kelowna, B.C. real estate market in early 2025 shows signs of recovery. Sales rose significantly, with January 2025 single-family home sales up 41% year over year, reaching 110 units, and October 2024 saw a 60% increase. Benchmark prices increased modestly, with single-family homes at $1,030,600 (up 5.4%) and condos at $517,700 (up 4.3%), though still below 2022 peaks. Inventory levels are high, with nine months of listings in September 2024, creating a buyer’s market, especially in the luxury segment. Interest rate cuts to 3% by January 2025 have boosted affordability, while new short-term rental regulations increased condo supply. Economic growth in the region was slow in 2024, but realty insiders predict a 4% sales increase and a 3% price rise in 2025. Affordability remains a challenge, and while move-up buyers drive mid-to-high range activity, first-time buyers focus on entry-level properties, signalling a cautiously optimistic, balanced market.”

Next, I tried ChatGPT. It did a 260-word analysis. Which I also asked it to condense to 150 words. This is what I got:

“The Kelowna real estate market is showing signs of renewed strength in early 2025. January saw a surge in sales activity, with single-family home sales up 41% year-over-year, townhouses up 35.7% and condos rising 10.5%. Benchmark prices have also increased: $1.03 million for single-family homes, $742,000 for townhomes, and $517,000 for condos. Milder weather, stabilized interest rates and improved buyer confidence have contributed to the market’s momentum. As of Feb. 1, 146 homes were listed for sale—6.8% more than the previous month—giving buyers more choice and indicating a more balanced market. While activity is rising, the market remains sensitive to affordability concerns and potential future rate changes. Overall, Kelowna’s real estate market appears to be recovering steadily with cautious optimism.”

Finally I asked Meta, which was the most concise weighing in at 215 words. Again I asked it to trim it down to 150 and here is the result:

“The Kelowna, B.C. real estate market is experiencing a mix of trends. Home prices have been relatively flat, with a median list price of $977,122 and an average price per square-foot of $486. The market is leaning in favour of buyers, with active listings at their highest level in three years and a sales-to-active listings ratio below 0.25. New listings are rising but home sales have been slower due to economic uncertainty. Mortgage rates remain relatively high, limiting buyer budgets and the rental market is experiencing upward pressure. Overall, the market is characterized by flat home prices, a buyer's market and rising new listings. For expert analysis, consider consulting a local real estate agent or economist.”

The first two are similar, with Meta straying and being more pessimistic. They all cited a few sources in their initial responses so I could see where they were getting some of the information.

In my opinion, a problem with the AI analysis is it depends on published open-source data that is often written by organizations that are cheerleading the results, hoping to assuage fears or massage the data to give their perspective. After all, if no one is buying real-estate, some businesses aren’t making any money, right? (I see what I believe to be just that in lots of real-estate articles).

I do not believe current raw MLS data is available, so the AI programs need to get the information from somewhere and if that information is inaccurate, well GIGO (garbage in, garbage out).

If you wonder why I don’t think AI has access to raw MLS data, I asked other questions and often I got the response, “I do not have access to that data.”

Real estate agents can pull data from the MLS system and pick it apart using their knowledge of local areas, as well as trends in pricing. Let’s say there is a large exclusive condo development that has several expensive units that sold recently. If you don’t take that into account, you may conclude pricing is going up for condos. But actually it is an outlier skewing the average.

I am sure many situations can cloud the waters when it comes to what is happening in a local real-estate market. I think having a living breathing person with local experience is still the best bet if you want advice on what is happening in your area.

There are still some headwinds for AI when it comes to being able to give advice about local market trends. When it can look at, and query, different databases, things may look different. Until then, I would stick with a local flesh and blood alternative.

Score: AI 0, humans 1

If you have suggestions for other real estate-related articles, please email me at: [email protected]

This article is written by or on behalf of an outsourced columnist and does not necessarily reflect the views of Castanet.

How AI systems are changing buying and selling real estate

AI revolutionizes real estate

The real estate market in British Columbia, and in general, is entering a new era, driven by artificial intelligence innovations that promise to streamline the buying and selling process.

From analyzing market trends to crafting marketing materials, AI systems are stepping up to assist buyers and sellers alike. At least that’s what we keep hearing.

Today, I will explore three prominent AI platforms—Grok (developed by xAI), ChatGPT (from OpenAI) and Meta AI—and what they claim they can do to transform real estate transactions. The key word here being “claim”. In future columns, I’ll put those systems to the test to see how claims stack up against results.

First, a little about the systems. I asked each one to describe itself after I asked it a few questions.

Here are the responses:

• Meta AI Sid it is “an artificial intelligence model designed to generate human-like responses, offering assistance and information on various topics, including real estate, marketing and more.”

• ChatGPT is “an AI assistant that helps with writing, research, planning, problem-solving, and more—offering fast, intelligent support across topics like real estate, business, travel, and everyday tasks.”

• Grok “analyzes real-time data, X posts, and content like photos/PDFs to offer tailored real estate insights, market trends, and decision-making support for B.C.’s Interior.”

Each one managed to refer back to previous topics they were questioned about, so at least I know they are good at trying to market themselves.

What they all claim

All three systems share a core set of capabilities that align with the needs of the real estate industry. They can process vast amounts of data quickly, offering insights into market trends, property values and buyer preferences. Each claim to assist with research and answer questions about local regulations. Additionally, they can provide scenario-based guidance—helping users weigh options like whether to buy now or wait for a market shift. Those foundational skills make AI a potential game-changer for anyone navigating British Columbia’s competitive housing landscape, from first-time buyers in Kamloops to sellers in the Okanagan.

Here is a list of the things each AI gave me when I asked it what it could do for buyers and sellers of real estate in B.C.’s Interior. These are the overlapping functionalities, either explicitly stated or implied with similar intent across Grok, Meta AI, and ChatGPT:

1. Market trend analysis

2. Pricing strategy guidance

3. Local regulation and zoning information

4. Marketing assistance for sellers

5. Comparable sales analysis

These five items reflect a baseline of AI support for real estate, focusing on market insights, pricing, regulations, and marketing.

Unique to Grok

• Search web and X for real-time info on property values

• Analyze listing photos or PDFs for property details

• Analyze X posts for local market sentiment

• Analyze uploaded content (e.g., home photos) for appeal

• Offer insights on up-and-coming neighbourhoods

• Provide pros and cons of buying now versus waiting

• Offer guidance on timing the sale

• Explain financing options like B.C. rural home loans

Unique to Meta AI

• Neighborhood guides

• Property search assistance

• Home inspection checklist

• Community information

• School district research

• Outdoor recreation information

• Local business and amenity guides

• Relocation advice

• Staging tips

• Real estate law explanations

• Tax implication information

• Contract guidance

• Closing cost estimates

• Seller's checklist

• Real estate terminology explanations

• Local market news and updates

• Recommended professionals

• Online resource guides

• FAQ and glossary

• General information about strata properties

• Information on rural and acreage properties

• Guidance on new construction and development

Unique to ChatGPT

• Area comparisons (e.g., Kamloops vs. Vernon)

• Property feature checklists

• First-time homebuyer program info

• Mortgage and cost calculators

• Questions to ask during showings

• Offer strategy suggestions

• Reviewing strata documents (plain language summaries)

• Assessing development or rental potential

• Community profiles (schools, lifestyle, amenities)

• Commute and travel time estimates

• Social media and ad copy for listings

• Pre-listing checklists (repairs, staging, photos)

• Open house scripts and talking points

• Email and text templates for following up with leads

• Explaining offer terms and conditions

• Seller net sheet estimation

• Guidance on navigating conditional offers

Testing the claims

While these AI systems sound impressive on paper, their real-world performance remains to be seen.

Can Grok truly spot a hot neighbourhood before it hits the mainstream? Will ChatGPT’s listing descriptions attract more buyers than a human agents? Can Meta really find that one great coffee shop with the best latte?

Over the next few columns, I’ll dig more into AI and how much it can actually help with buying and selling real estate. I’ll task it with analyzing listings, researching local markets and assisting with hypothetical real estate transactions across the British Columbia interior.

We’ll see how they stack up against each other and make sure that they perform as advertised.

If you have suggestions for other real estate-related articles, please email me at [email protected].

This article is written by or on behalf of an outsourced columnist and does not necessarily reflect the views of Castanet.