Using AI to help stage and advertise your home for sale

AI as a home-selling tool

Photo: The Canadian Press

While AI can offer advice about how to sell your home, use of a human realtor can be more advantageous says columnist Anthony Shephard.

Today, I have another instalment of “In AI we trust…or maybe it’s AI are a bust.” I will get a little closer to answering that today.

Todays quest for the three AI platforms, Grok from X, ChatGPT from Open AI and Meta AI from Meta, is marketing. I asked, “I am planning to sell my home at (insert address) in Kelowna, what kind of marketing assistance can you give me?”

First up was Grok. It weighed in at a hefty 1,478 words which I asked it to pare down to 150.

To market the home, a 1,994-square-foot, four-bedroom house on a 9,757-square-foot lot in Black Mountain, leverage a tailored strategy, it said. It added, price competitively using a comparative market analysis, targeting $600,000 to $800,000, and highlight the spacious lot. Use professional photography, virtual staging and MLS listings on Realter.ca. Promote via social media ads, local realtor, and guerrilla tactics, like handwritten letters or community flyers. Host themed open houses to attract families. Engage a Kelowna real estate agent for negotiation and networks. Use AI tools like Grok for listing descriptions or market trends. Stage the home, enhance curb appeal, and ensure legal disclosures. Launch within four to six weeks, monitoring market shifts. It said it could draft content, analyze documents and provide real-time market updates to refine your approach.

ChatGPT came up with 259 words and after the usual trim to 150 words, I was left with this.

It said it could can help market the home with professionally written listing descriptions, catchy headlines, and tailored content for MLS social media and email campaigns. It would provide guidance about photographs, staging, key features to highlight and help design flyers or feature sheets for open houses. For online visibility, it could create compelling social media captions, suggest hashtags and help craft messages for buyer follow-ups and inquiries. It said I would also receive support with local lifestyle write-ups, showcasing nearby amenities like parks, schools, and downtown access. Additionally, it could help draft price positioning language, offer communication tips for open houses and provide tools to respond to market feedback. Whether aiming to attract families, downsizers, or investors, it could help highlight what makes the home and location unique clearly and persuasively.

Rounding out the field was Meta with a concise 226 words and when trimmed down said to market the home consider the following:

• Online presence: Use high-quality photos and virtual tours on online listings like Realtor.ca and Zolo.ca.

• Social media: Share photos and details on Facebook and Instagram and use targeted ads to reach potential buyers.

• Staging and presentation: Declutter, depersonalize and highlight upgrades and unique features.

• Local exposure: Host open houses and consider working with a local real estate agent.

• Neighbourhood information: Emphasize the benefits of living in your neighbourhood, such as nearby parks and amenities.

Working with a local real estate agent could provide personalized guidance and help navigate the Kelowna market. By showcasing the home's best features and reaching potential buyers, it could increase the chance of selling the home quickly and for a good price.

I will say they all seemed reasonably consistent but for me the responses were underwhelming. In my experience, working with a real estate agent will help and they will discuss all of these same things.They can tailor their advice and suggestions to your particular home and property.

Two out of the three recommended hiring a real estate agent in their initial responses, so I agree with that. As you have seen in past columns, help with pricing is best left to an agent at this point and AI isn’t always accurate with neighbourhoods.

This week I would say it is close but definitely, for me, I am going to give the point to the humans so it looks like the Score AI one and humans three.

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.

B.C. real estate market slows as listings outpace sales

Moving to a buyers' market

Photo: Pixabay

Supply of homes for sale is growing but demand is slowing in B.C..

I have had lots of questions about the market recently, so I decided to do another market breakdown for the B.C. Interior. The last one I did was in February.

I am not a cheerleader and I’m not going to tell you this is a great time to buy or to sell. I have noticed that no matter the market, many real estate articles written by people in the industry end with how it is great news, no matter what the news is. Sorry, you won’t find that here, I am just going to give you the facts. Draw your own conclusions.

The latest seven-day snapshot of the British Columbia real estate market shows a cooling trend, with inventory rising while buyer activity slows. The new listings-to-sales ratio climbed to 2.74:1, a signal the market is tilting further into buyer’s territory.

Current market breakdown (last week’s data is about delayed by seven days)

Total residential listings by price range:

• Up to $250,000: 697

• $250,001-$500,000: 2,051

• $500,001-$1,000,000: 4,518

• $1,000,001-$2,000,000: 2,185

• More than $2,000,001: 624
Total active listings: 10,075

Total residential sales during the time period: 230

• Up to $250,000: 19

• $250,001-$500,000: 54

• $500,001-$1,000,000: 117

• $1,000,001-$2,000,000: 38

• More than $2,000,001: 2

New total listings during the week: 952. Sales during the week: 347
New total listings-to-sales ratio: 2.74:1
Current residential listings-to-sales ratio: 10,075 ÷ 230 ≈ 43.8:1

(please note that new total listing are of all types, not just residential)

This sharp contrast between active inventory and buyer activity reflects a slower-paced market. Homes priced between $500,000 and $1 million continue to see the most movement, representing more than 50% of weekly sales, though sales volume in that range dropped from to 117 from 151 compared to the previous period.

The luxury segment remains the softest, with only two sales of property priced over $2 million out of 624 listings. Similarly, the entry-level market (up to $250,000) had just 19 sales out of 697 listings, suggesting supply is outpacing demand across all categories.

Comparison to the previous period

In the seven-day period in February:

• Total residential listings were 9,444

• Total residential sales were 317

• The new listings-to-sales ratio: 1.63:1

• The total listings-to-sales ratio was 9,444 ÷ 317 ≈ 29.8:1

• Inventory has increased by over 600 listings.

This shift suggests buyer hesitation is not improving, m. Many of us thought waiting for interest rate decisions, political outcomes, etc. added to buyer hesitation. With several of those things behind us and spring a typically busy time of year, I expected things to improve.

It is still early however. We will see what transpires in the next few weeks. Right now, B.C.’s housing market appears to be cooling, with slowing sales and climbing inventory. The current ratios strongly favour buyers, particularly in the higher and lower price brackets. For sellers, strategic pricing and property presentation are now more crucial than ever. For buyers, this could be an opportune time to negotiate in a less competitive landscape. (OK, maybe a little cheerleading, I couldn’t help it.)

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.

Asking AI about real estate zoning

AI and real estate

Photo: Contributed

Some AI tools are more helpful than others when it comes to getting information about real estate and municipal zoning.

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

Photo: Pixabay

Artificial intelligence may or may not be useful for pricing property, depending on the program one uses.

In my last few columns, I wrote about artificial intelligence or “bots,” and their uses for real estate selling, buying etc.

I looked at Grok from X , ChatGPT and Meta’s AI. There are other AI programs out there like Claude, Gemini, DeepSeek, Perplexity, Alexa, Cortana and more.

I decided to stay with what I consider to be the most popular but feel free to take a look at these other ones if they interest you.

This week, I asked the bots to determine a fair market value for one of my listings, in Kelowna. I put in the actual address and let them do their thing.

First up was Grok 3. It went all out and came up with 625 words which I asked to be trimmed down to 150 words.

“To price the home at (the address in Kelowna) I analyzed its 2,527-square-feet size, five bedrooms, 3.5 bathrooms and 9,583-square-foot lot in Black Mountain. Comparables on (the same road) show smaller homes (1,369 square-feet to 1,853 square-feet) valued at $854,100 to $908,800 in 2023–24. Kelowna’s January 2025 benchmark price for single-family homes is $1,030,600, up 5.4% year-over-year, but Black Mountain is slightly below average. Using a $490-square-foot to $550-square-foot range from comps, the home’s value is $1,238,230 to $1,389,850. High inventory (nine months as of September 2024) indicates a buyer’s market, so pricing competitively is key. The large lot and family-friendly features add value but an older home may need updates. I recommend listing at $1,199,000, balancing size, location, and market conditions. If renovated, $1,250,000 could work, but adjust if it sits. Consult a local realtor for precision.”

Its worth noting the home is in north Rutland, not Black Mountain, so Grok seems to be a little location challenged. I think the next version may need a GPS built in.

Stepping up to the plate next was Meta’s AI

“To provide a more accurate pricing suggestion (for the home), I'd need more information about the property. Here are some questions to consider:

What type of property is it (single-family home, townhouse, condo)?

What is the square footage of the property?

How many bedrooms and bathrooms does it have?

What is the age and condition of the property?

Are there any notable features (views, pool, etc.)?

What is the current state of the local real estate market?

You can also check websites like:

B.C. Assessment

Zestimate (Zillow)

These resources can give you an estimate based on recent sales data and property characteristics.

For a more precise valuation, consider consulting a local real estate agent.”

So, basically it just said I don’t know, ask someone else. But it took 134 words to do it. That sounds like some politicians you might know. A little tongue in cheek I know, however, the other AI programs did find out more about the property on their own and Meta’s AI didn’t try hard at all.

Last up to bat was ChatGPT, which took 334 words and the response paired down to 150 words was:

“Nearby comparable properties range from $789,000 to $1,125,000. For example, (a nearby home) (1,347 square-feet) is listed at $789,000, and (another nearby home) (2,452 square-feet) is priced at $900,000. Larger homes with suites or corner lots push closer to $1.1 million. Based on size, updates, and location, an estimated value between $900,000 and $950,000 is reasonable.

For an accurate price, a local real estate agent can provide a comparative market analysis factoring in renovations, lot utility and market timing. This helps position the home competitively for a successful sale.”

The answers ranged from $1.25 million to I have no idea to between 900,000 to 950,000. ChatGPT seemed to be in the ballpark, relying on list prices of nearby properties.

List prices, as you know, are usually determined by real estate agents and their clients, so ultimately it derived its price from prices people set. If this were a school assignment, I think I might say that is using someone else’s work or cheating.

In the end the market determines the price. When someone agrees to buy a property at a certain price, until then a true value hasn’t been set. As agents, we aim to price listings in the ballpark so the market can view the property and decide its value.

In today's market, with more inventory than buyers, overpriced homes can sit for a long time, waiting for that one perfect buyer. If a quicker sale is needed, pricing lower attracts more buyers who are often more flexible but expect a better deal. That is why an agent is valuable, not just to assess the property but also to understand the seller’s priorities and work with the client to achieve their goals.

I am going to say it was another swing and a miss for AI this time.

Score: AI zero and humans two.

If you have suggestions for other real estate-related columns, 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.