{"id":31,"date":"2026-09-20T12:50:06","date_gmt":"2026-09-20T12:50:06","guid":{"rendered":"https:\/\/borstev.com\/blog\/?p=31"},"modified":"2026-09-20T19:12:30","modified_gmt":"2026-09-20T19:12:30","slug":"ai-agent-for-real-estate-5-questions","status":"publish","type":"post","link":"https:\/\/borstev.com\/blog\/ai-agent-for-real-estate-5-questions\/","title":{"rendered":"AI Agent for Real Estate: 5 Questions to Ask Before You Deploy One"},"content":{"rendered":"\n<figure class=\"wp-block-embed is-type-video is-provider-youtube wp-block-embed-youtube wp-embed-aspect-16-9 wp-has-aspect-ratio\"><div class=\"wp-block-embed__wrapper\">\n<iframe loading=\"lazy\" title=\"Real Estate Automation Is Failing: 5 Questions That Save Your AI Agent\" width=\"500\" height=\"281\" src=\"https:\/\/www.youtube.com\/embed\/HD5qq4di6Os?feature=oembed\" frameborder=\"0\" allow=\"accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture; web-share\" referrerpolicy=\"strict-origin-when-cross-origin\" allowfullscreen><\/iframe>\n<\/div><\/figure>\n\n\n\n<hr class=\"wp-block-separator has-alpha-channel-opacity\"\/>\n\n\n\n<p class=\"wp-block-paragraph\">If you are about to put an AI agent for real estate lead follow-up in front of your buyers, one number should stop you before you flip the switch. Roughly 88% of AI agents never reach production, according to IDC&#8217;s research on enterprise AI pilots. That number is less about whether AI works and more about how much planning most people skip before they build anything.<\/p>\n\n\n\n<p class=\"wp-block-paragraph\">The failure usually traces back to planning, not the model. Skip that part and you end up building the next entry in that <a href=\"https:\/\/bex.co\/blog\/2026\/09\/10\/ai-agent-pilots-production-deployment-gate\" target=\"_blank\" rel=\"noopener\">88%<\/a>, not an AI agent for real estate that actually works.<\/p>\n\n\n\n<p class=\"wp-block-paragraph\">Picture a lead who fills out a form at eleven at night asking about a listing. By the time anyone calls back the next morning, that person has already toured a comparable house with a different agent. This is exactly the moment an AI agent is supposed to fix, replying instantly, asking the right questions, getting them booked before they go cold. It can do that, but only once you have answered five questions that most agencies never get asked.<\/p>\n\n\n\n<div id=\"ez-toc-container\" class=\"ez-toc-v2_0_88 counter-hierarchy ez-toc-counter ez-toc-grey ez-toc-container-direction\">\n<div class=\"ez-toc-title-container\">\n<p class=\"ez-toc-title\" style=\"cursor:inherit\">Table of Contents<\/p>\n<span class=\"ez-toc-title-toggle\"><a href=\"#\" class=\"ez-toc-pull-right ez-toc-btn ez-toc-btn-xs ez-toc-btn-default ez-toc-toggle\" aria-label=\"Toggle Table of Content\"><span class=\"ez-toc-js-icon-con\"><span class=\"\"><span class=\"eztoc-hide\" style=\"display:none;\">Toggle<\/span><span class=\"ez-toc-icon-toggle-span\"><svg style=\"fill: #999;color:#999\" xmlns=\"http:\/\/www.w3.org\/2000\/svg\" class=\"list-377408\" width=\"20px\" height=\"20px\" viewBox=\"0 0 24 24\" fill=\"none\"><path d=\"M6 6H4v2h2V6zm14 0H8v2h12V6zM4 11h2v2H4v-2zm16 0H8v2h12v-2zM4 16h2v2H4v-2zm16 0H8v2h12v-2z\" fill=\"currentColor\"><\/path><\/svg><svg style=\"fill: #999;color:#999\" class=\"arrow-unsorted-368013\" xmlns=\"http:\/\/www.w3.org\/2000\/svg\" width=\"10px\" height=\"10px\" viewBox=\"0 0 24 24\" version=\"1.2\" baseProfile=\"tiny\"><path d=\"M18.2 9.3l-6.2-6.3-6.2 6.3c-.2.2-.3.4-.3.7s.1.5.3.7c.2.2.4.3.7.3h11c.3 0 .5-.1.7-.3.2-.2.3-.5.3-.7s-.1-.5-.3-.7zM5.8 14.7l6.2 6.3 6.2-6.3c.2-.2.3-.5.3-.7s-.1-.5-.3-.7c-.2-.2-.4-.3-.7-.3h-11c-.3 0-.5.1-.7.3-.2.2-.3.5-.3.7s.1.5.3.7z\"\/><\/svg><\/span><\/span><\/span><\/a><\/span><\/div>\n<nav><ul class='ez-toc-list ez-toc-list-level-1 ' ><li class='ez-toc-page-1 ez-toc-heading-level-2'><a class=\"ez-toc-link ez-toc-heading-1\" href=\"https:\/\/borstev.com\/blog\/ai-agent-for-real-estate-5-questions\/#Why_%E2%80%9Cjust_let_the_AI_handle_it%E2%80%9D_doesnt_work\" >Why &#8220;just let the AI handle it&#8221; doesn&#8217;t work<\/a><\/li><li class='ez-toc-page-1 ez-toc-heading-level-2'><a class=\"ez-toc-link ez-toc-heading-2\" href=\"https:\/\/borstev.com\/blog\/ai-agent-for-real-estate-5-questions\/#Question_one_what_should_this_agent_never_do\" >Question one: what should this agent never do?<\/a><\/li><li class='ez-toc-page-1 ez-toc-heading-level-2'><a class=\"ez-toc-link ez-toc-heading-3\" href=\"https:\/\/borstev.com\/blog\/ai-agent-for-real-estate-5-questions\/#Question_two_where_does_your_judgment_stay\" >Question two: where does your judgment stay?<\/a><\/li><li class='ez-toc-page-1 ez-toc-heading-level-2'><a class=\"ez-toc-link ez-toc-heading-4\" href=\"https:\/\/borstev.com\/blog\/ai-agent-for-real-estate-5-questions\/#Question_three_what_does_%E2%80%9Cworking%E2%80%9D_actually_look_like\" >Question three: what does &#8220;working&#8221; actually look like?<\/a><\/li><li class='ez-toc-page-1 ez-toc-heading-level-2'><a class=\"ez-toc-link ez-toc-heading-5\" href=\"https:\/\/borstev.com\/blog\/ai-agent-for-real-estate-5-questions\/#Question_four_what_does_it_actually_need_access_to\" >Question four: what does it actually need access to?<\/a><\/li><li class='ez-toc-page-1 ez-toc-heading-level-2'><a class=\"ez-toc-link ez-toc-heading-6\" href=\"https:\/\/borstev.com\/blog\/ai-agent-for-real-estate-5-questions\/#Question_five_who_watches_for_drift_and_how_often\" >Question five: who watches for drift, and how often?<\/a><\/li><li class='ez-toc-page-1 ez-toc-heading-level-2'><a class=\"ez-toc-link ez-toc-heading-7\" href=\"https:\/\/borstev.com\/blog\/ai-agent-for-real-estate-5-questions\/#What_changes_when_you_get_this_right\" >What changes when you get this right<\/a><\/li><li class='ez-toc-page-1 ez-toc-heading-level-2'><a class=\"ez-toc-link ez-toc-heading-8\" href=\"https:\/\/borstev.com\/blog\/ai-agent-for-real-estate-5-questions\/#The_five_questions_at_a_glance\" >The five questions, at a glance<\/a><\/li><li class='ez-toc-page-1 ez-toc-heading-level-2'><a class=\"ez-toc-link ez-toc-heading-9\" href=\"https:\/\/borstev.com\/blog\/ai-agent-for-real-estate-5-questions\/#FAQ\" >FAQ<\/a><\/li><li class='ez-toc-page-1 ez-toc-heading-level-2'><a class=\"ez-toc-link ez-toc-heading-10\" href=\"https:\/\/borstev.com\/blog\/ai-agent-for-real-estate-5-questions\/#Get_the_audit\" >Get the audit<\/a><\/li><\/ul><\/nav><\/div>\n<h2 class=\"wp-block-heading\"><span class=\"ez-toc-section\" id=\"Why_%E2%80%9Cjust_let_the_AI_handle_it%E2%80%9D_doesnt_work\"><\/span>Why &#8220;just let the AI handle it&#8221; doesn&#8217;t work<span class=\"ez-toc-section-end\"><\/span><\/h2>\n\n\n\n<p class=\"wp-block-paragraph\">The instinct with any new AI tool is to hand it a goal and let it figure out the rest. Find leads. Handle follow-ups. Qualify buyers. Then step back and see what happens.<\/p>\n\n\n\n<p class=\"wp-block-paragraph\">I build AI agents for real estate businesses for a living, and this is the pattern I see most often. A client comes to me and says they want an AI agent that answers their leads. When I ask what a good answer actually looks like, they usually cannot tell me. If we build against that, the AI agent has nothing to aim at.<\/p>\n\n\n\n<p class=\"wp-block-paragraph\">The second problem shows up right after: the agent only works with what it can actually reach. Hand it a messy CRM and it pulls messy answers from that CRM, then guesses at the rest. I made this exact mistake on one of my own agents recently. I told it clearly what to search for and never told it what to leave out. The AI did exactly what I asked it to do. I just forgot to tell it what to skip, and that ended up costing me a pile of data I couldn&#8217;t use, which was on me, not the tool.<\/p>\n\n\n\n<p class=\"wp-block-paragraph\">Most people never draw a boundary line at all. They describe what they want the agent to do and stop there, without ever saying what it should never do. Below are the five questions that decide whether your AI agent for real estate ends up in the 12% that works or the 88% that doesn&#8217;t.<\/p>\n\n\n\n<h2 class=\"wp-block-heading\"><span class=\"ez-toc-section\" id=\"Question_one_what_should_this_agent_never_do\"><\/span>Question one: what should this agent never do?<span class=\"ez-toc-section-end\"><\/span><\/h2>\n\n\n\n<p class=\"wp-block-paragraph\">The instinct is to start by describing the goal. Handle follow-ups, qualify buyers, book showings, then let the agent work out the how. That order is backwards.<\/p>\n\n\n\n<p class=\"wp-block-paragraph\">Say you build an agent to follow up with people who inquired about a listing, and all you told it was &#8220;help these leads.&#8221; Left with only that instruction, it might confirm a showing time on its own, or worse, tell someone a property is still available when it isn&#8217;t. Inventory changes hourly. If a unit went under contract that same morning and your agent confidently tells a buyer it&#8217;s still available and offers to schedule a tour, that costs you trust fast, and it can turn into a legal problem just as quickly.<\/p>\n\n\n\n<p class=\"wp-block-paragraph\">The rule can&#8217;t be &#8220;help the lead.&#8221; It has to be: gather interest, answer general questions, and never make a commitment on price, availability, or scheduling before a human confirms it. Start every AI agent for real estate with what it must never touch, not with what it should do. That single boundary keeps you away from the mistakes that actually hurt a business.<\/p>\n\n\n\n<h2 class=\"wp-block-heading\"><span class=\"ez-toc-section\" id=\"Question_two_where_does_your_judgment_stay\"><\/span>Question two: where does your judgment stay?<span class=\"ez-toc-section-end\"><\/span><\/h2>\n\n\n\n<p class=\"wp-block-paragraph\">Even once an agent is accurate, some decisions still need to stay with a person. The AI can be plenty smart and still lack your experience of which calls, in your specific business, carry the most risk.<\/p>\n\n\n\n<p class=\"wp-block-paragraph\">Take a decision that sounds harmless and isn&#8217;t: an agent that recommends listings to buyers based on what similar past clients liked. On the surface that&#8217;s just smart personalization. In practice it&#8217;s one of the more dangerous things you can automate, because &#8220;similar clients&#8221; in historical housing data is never a neutral pattern. Decades of housing segregation are baked into who bought where. If an agent starts steering buyers toward or away from neighborhoods based on correlations that quietly track race, nobody typed anything about race into the system, and the AI didn&#8217;t decide to discriminate. It found a pattern and optimized for it. It can be fully accurate and still be a Fair Housing Act violation.<\/p>\n\n\n\n<p class=\"wp-block-paragraph\">That&#8217;s why some calls have to stay yours. The license on the line is yours, not the model&#8217;s. Before you build anything, write down the specific decisions you are keeping for a human, and don&#8217;t let the agent quietly absorb them later just because it seems capable enough.<\/p>\n\n\n\n<h2 class=\"wp-block-heading\"><span class=\"ez-toc-section\" id=\"Question_three_what_does_%E2%80%9Cworking%E2%80%9D_actually_look_like\"><\/span>Question three: what does &#8220;working&#8221; actually look like?<span class=\"ez-toc-section-end\"><\/span><\/h2>\n\n\n\n<p class=\"wp-block-paragraph\">Almost everyone starts with &#8220;I want this to work well.&#8221; That&#8217;s a feeling, not a target, and if you can&#8217;t say precisely what success looks like, you have no way to notice when the agent stops hitting it.<\/p>\n\n\n\n<p class=\"wp-block-paragraph\"><a href=\"https:\/\/forkast.news\/the-agent-production-gap-when-171-roi-isnt-enough-to-ship\/\" target=\"_blank\" rel=\"noopener\">Forrester<\/a>&#8216;s research on AI deployments found that 41% of projects with negative ROI after twelve months trace back to exactly this problem, no defined success criteria. &#8220;Fast replies&#8221; has to mean something specific: replies within five minutes, with the correct information, correctly identifying buy intent versus sell intent at least 95% of the time. Without that bar, an agent can look like it&#8217;s succeeding while it&#8217;s actually leaking clients.<\/p>\n\n\n\n<p class=\"wp-block-paragraph\">This is what that looks like in practice. A lead asks for an offer estimate. The agent replies in five minutes, which is easy, but the reply is incomplete. The lead moves on to the next agency. Nothing about the interaction looks broken on the surface, the agent replied fast and sounded helpful, and nobody notices for weeks that it&#8217;s costing you deals with every lead it touches. Without a specific number to check against, you won&#8217;t catch the agent slipping until a client already has.<\/p>\n\n\n\n<h2 class=\"wp-block-heading\"><span class=\"ez-toc-section\" id=\"Question_four_what_does_it_actually_need_access_to\"><\/span>Question four: what does it actually need access to?<span class=\"ez-toc-section-end\"><\/span><\/h2>\n\n\n\n<p class=\"wp-block-paragraph\">This is the least exciting question on the list, and the one people skip most often, right before it becomes the reason the whole project stalls.<\/p>\n\n\n\n<p class=\"wp-block-paragraph\">You know what you want the agent to accomplish. You don&#8217;t always think through what it needs to see to get there. If an agent is supposed to sound like it knows the client, and it can&#8217;t see the full conversation history across every past call and message, it will ask something the buyer already answered three days ago. Picture a buyer who already said &#8220;we told you we need a fenced yard for the dog,&#8221; and the agent asks about pet policies again like it&#8217;s the first conversation. That wastes time and signals that nobody is paying attention, which is the last impression you want to give someone making the biggest purchase of their life.<\/p>\n\n\n\n<p class=\"wp-block-paragraph\">If your CRM is already the problem here, fixing the data comes before fixing the agent. I wrote a full walkthrough of that cleanup process in <a href=\"\/dead-leads-real-estate-crm-ai\">this piece on reviving dead CRM leads<\/a>, and the same audit applies directly to what an AI agent for real estate needs before it can sound like it&#8217;s paying attention.<\/p>\n\n\n\n<p class=\"wp-block-paragraph\">Map out exactly what the agent needs to touch before you build the exciting part, not what you want it to accomplish but what it actually needs in order to attempt it.<\/p>\n\n\n\n<h2 class=\"wp-block-heading\"><span class=\"ez-toc-section\" id=\"Question_five_who_watches_for_drift_and_how_often\"><\/span>Question five: who watches for drift, and how often?<span class=\"ez-toc-section-end\"><\/span><\/h2>\n\n\n\n<p class=\"wp-block-paragraph\">This is the question nobody wants to hear, because it means the work doesn&#8217;t end at launch. Treat an AI agent for real estate like a new hire, not a finished product. It needs coaching, correction, and time to learn how your business actually runs, and even a good agent can drift once it&#8217;s live. You usually won&#8217;t notice until a client complains or a deal quietly falls through the cracks, and even then it can take a while to figure out why.<\/p>\n\n\n\n<p class=\"wp-block-paragraph\">Imagine an agent trained during a slow market, where homes sit for sixty days and a relaxed follow-up pace felt right. Then the market shifts, homes start moving in a week, and nobody retrains the agent. It keeps the old slow pace while hot listings fly off the market, and leads go cold waiting on a rhythm that used to be fine and now just looks unresponsive. Someone has to check the agent&#8217;s behavior against current reality on a real schedule, weekly or every two weeks, not only when something visibly breaks. By the time it visibly breaks, it has already cost you something.<\/p>\n\n\n\n<h2 class=\"wp-block-heading\"><span class=\"ez-toc-section\" id=\"What_changes_when_you_get_this_right\"><\/span>What changes when you get this right<span class=\"ez-toc-section-end\"><\/span><\/h2>\n\n\n\n<p class=\"wp-block-paragraph\">Show Image<\/p>\n\n\n\n<p class=\"wp-block-paragraph\">One real estate business I worked with was losing leads simply because nobody could answer after hours, weekends, or holidays. Their average response time to a new inquiry was twelve hours. After we deployed a voice AI agent built around the five questions above, defined boundaries, a clear success bar, full access to conversation history, and a monitoring cadence, that dropped to five to ten minutes, and conversion from that lead source increased more than tenfold. That result came from the planning behind it, not a smarter model underneath it.<\/p>\n\n\n\n<h2 class=\"wp-block-heading\"><span class=\"ez-toc-section\" id=\"The_five_questions_at_a_glance\"><\/span>The five questions, at a glance<span class=\"ez-toc-section-end\"><\/span><\/h2>\n\n\n\n<figure class=\"wp-block-table\"><table class=\"has-fixed-layout\"><thead><tr><th>Question<\/th><th>What to nail down before you build<\/th><\/tr><\/thead><tbody><tr><td>What should it never do?<\/td><td>The specific commitments (price, availability, scheduling) it can never make without a human<\/td><\/tr><tr><td>Where does your judgment stay?<\/td><td>The decisions that carry legal or reputational risk, written down in advance<\/td><\/tr><tr><td>What does working look like?<\/td><td>A measurable bar, not a feeling, e.g. reply time plus accuracy rate<\/td><\/tr><tr><td>What does it need access to?<\/td><td>Full conversation history and the data it needs to sound like it&#8217;s paying attention<\/td><\/tr><tr><td>Who watches for drift?<\/td><td>A named person and a real schedule, weekly or bi-weekly, not &#8220;whenever something breaks&#8221;<\/td><\/tr><\/tbody><\/table><\/figure>\n\n\n\n<h2 class=\"wp-block-heading\"><span class=\"ez-toc-section\" id=\"FAQ\"><\/span>FAQ<span class=\"ez-toc-section-end\"><\/span><\/h2>\n\n\n\n<p class=\"wp-block-paragraph\"><strong>How many AI agent projects actually fail before reaching production?<\/strong><\/p>\n\n\n\n<p class=\"wp-block-paragraph\">Roughly 88%, according to IDC&#8217;s research on enterprise AI proofs of concept, a figure independently supported by similar findings from RAND and a Forrester and Anaconda analysis in the 86 to 88% range.<\/p>\n\n\n\n<p class=\"wp-block-paragraph\"><strong>Is it legal for an AI agent to recommend listings based on what similar past clients bought?<\/strong><\/p>\n\n\n\n<p class=\"wp-block-paragraph\">It can easily become a Fair Housing Act problem. Historical buying patterns often correlate with race due to decades of housing segregation, so an agent optimizing on &#8220;similar clients&#8221; can steer buyers by neighborhood without anyone intending it to. Keep listing recommendations and any judgment call tied to protected classes with a human.<\/p>\n\n\n\n<p class=\"wp-block-paragraph\"><strong>What should an AI agent for real estate never do on its own?<\/strong><\/p>\n\n\n\n<p class=\"wp-block-paragraph\">Confirm a showing time, quote a firm price, or state that a property is still available without checking current status with a human first. Its job is to gather interest and answer general questions, not to make commitments.<\/p>\n\n\n\n<p class=\"wp-block-paragraph\"><strong>How do I know if my AI agent for real estate is actually working?<\/strong><\/p>\n\n\n\n<p class=\"wp-block-paragraph\">Only if you defined &#8220;working&#8221; as a measurable bar before launch, for example a reply time under five minutes with a minimum accuracy rate on identifying buyer versus seller intent. Without a specific target, an agent can look fine on the surface while quietly losing you deals.<\/p>\n\n\n\n<p class=\"wp-block-paragraph\"><strong>Do I still need to monitor an AI agent after it launches?<\/strong><\/p>\n\n\n\n<p class=\"wp-block-paragraph\">Yes. Markets shift, and an agent trained for a slow market will keep a slow pace even after listings start moving fast. Someone needs to check its behavior against current conditions on a set schedule, not only after something visibly breaks.<\/p>\n\n\n\n<hr class=\"wp-block-separator has-alpha-channel-opacity\"\/>\n\n\n\n<h2 class=\"wp-block-heading\"><span class=\"ez-toc-section\" id=\"Get_the_audit\"><\/span>Get the audit<span class=\"ez-toc-section-end\"><\/span><\/h2>\n\n\n\n<p class=\"wp-block-paragraph\">Before we touch a client&#8217;s AI agent, we run this exact process: find the gaps first, the messy CRM, the unanswered calls, the missing follow-up rules, then answer these five questions. That is the difference between the 12% and the 88%.<\/p>\n\n\n\n<p class=\"wp-block-paragraph\">If you want us to run this audit on your business, <a href=\"https:\/\/calendly.com\/bogomil-stoev\/custom-ai-agents\" target=\"_blank\" rel=\"noopener\">book a call<\/a>.<\/p>\n\n\n\n<script type=\"application\/ld+json\">\n{\n  \"@context\": \"https:\/\/schema.org\",\n  \"@graph\": [\n    {\n      \"@type\": \"Article\",\n      \"headline\": \"AI Agent for Real Estate: 5 Questions to Ask Before You Deploy One\",\n      \"description\": \"The five questions that decide whether an AI agent for real estate lead follow-up actually works, or joins the 88% of AI agents that never reach production.\",\n      \"author\": {\n        \"@type\": \"Person\",\n        \"name\": \"Bogomil [SURNAME]\",\n        \"url\": \"https:\/\/[YOURSITE]\/about\",\n        \"sameAs\": [\n          \"https:\/\/www.linkedin.com\/in\/[YOUR-LI]\/\",\n          \"https:\/\/www.youtube.com\/@[YOUR-CHANNEL]\"\n        ],\n        \"jobTitle\": \"AI Agent Consultant\",\n        \"knowsAbout\": [\"AI agents\", \"Real estate lead generation\", \"CRM automation\", \"AI agent deployment\"]\n      },\n      \"publisher\": {\n        \"@type\": \"Organization\",\n        \"name\": \"[YOUR COMPANY]\",\n        \"url\": \"https:\/\/[YOURSITE]\"\n      },\n      \"datePublished\": \"[YYYY-MM-DD]\",\n      \"dateModified\": \"[YYYY-MM-DD]\",\n      \"mainEntityOfPage\": \"https:\/\/[YOURSITE]\/ai-agent-for-real-estate-5-questions\"\n    },\n    {\n      \"@type\": \"VideoObject\",\n      \"name\": \"[YOUTUBE VIDEO TITLE]\",\n      \"description\": \"[YOUTUBE DESCRIPTION, first 160 chars]\",\n      \"thumbnailUrl\": \"https:\/\/i.ytimg.com\/vi\/[VIDEO_ID]\/maxresdefault.jpg\",\n      \"uploadDate\": \"[YYYY-MM-DDT00:00:00+02:00]\",\n      \"duration\": \"PT[M]M[S]S\",\n      \"embedUrl\": \"https:\/\/www.youtube.com\/embed\/[VIDEO_ID]\",\n      \"contentUrl\": \"https:\/\/www.youtube.com\/watch?v=[VIDEO_ID]\",\n      \"transcript\": \"[FULL TRANSCRIPT TEXT]\"\n    },\n    {\n      \"@type\": \"FAQPage\",\n      \"mainEntity\": [\n        {\"@type\":\"Question\",\"name\":\"How many AI agent projects actually fail before reaching production?\",\"acceptedAnswer\":{\"@type\":\"Answer\",\"text\":\"Roughly 88%, according to IDC's research on enterprise AI proofs of concept, a figure independently supported by similar findings from RAND and a Forrester and Anaconda analysis in the 86 to 88% range.\"}},\n        {\"@type\":\"Question\",\"name\":\"Is it legal for an AI agent to recommend listings based on what similar past clients bought?\",\"acceptedAnswer\":{\"@type\":\"Answer\",\"text\":\"It can easily become a Fair Housing Act problem. Historical buying patterns often correlate with race due to decades of housing segregation, so an agent optimizing on similar clients can steer buyers by neighborhood without anyone intending it to. Keep listing recommendations and any judgment call tied to protected classes with a human.\"}},\n        {\"@type\":\"Question\",\"name\":\"What should an AI agent for real estate never do on its own?\",\"acceptedAnswer\":{\"@type\":\"Answer\",\"text\":\"Confirm a showing time, quote a firm price, or state that a property is still available without checking current status with a human first. Its job is to gather interest and answer general questions, not to make commitments.\"}},\n        {\"@type\":\"Question\",\"name\":\"How do I know if my AI agent for real estate is actually working?\",\"acceptedAnswer\":{\"@type\":\"Answer\",\"text\":\"Only if you defined working as a measurable bar before launch, for example a reply time under five minutes with a minimum accuracy rate on identifying buyer versus seller intent. Without a specific target, an agent can look fine on the surface while quietly losing you deals.\"}},\n        {\"@type\":\"Question\",\"name\":\"Do I still need to monitor an AI agent after it launches?\",\"acceptedAnswer\":{\"@type\":\"Answer\",\"text\":\"Yes. Markets shift, and an agent trained for a slow market will keep a slow pace even after listings start moving fast. Someone needs to check its behavior against current conditions on a set schedule, not only after something visibly breaks.\"}}\n      ]\n    }\n  ]\n}\n<\/script>\n\n\n\n<script type=\"application\/ld+json\">\n{\n  \"@context\": \"https:\/\/schema.org\",\n  \"@graph\": [\n    {\n      \"@type\": \"Article\",\n      \"headline\": \"AI Agent for Real Estate: 5 Questions to Ask Before You Deploy One\",\n      \"description\": \"The five questions that decide whether an AI agent for real estate lead follow-up actually works, or joins the 88% of AI agents that never reach production.\",\n      \"author\": {\n        \"@type\": \"Person\",\n        \"name\": \"Bogomil Stoev\",\n        \"url\": \"https:\/\/borstev.com\/about\",\n        \"sameAs\": [\n          \"https:\/\/www.linkedin.com\/in\/bogomils\/,\n          \"https:\/\/www.youtube.com\/@borstev\"\n        ],\n        \"jobTitle\": \"AI Agent Consultant\",\n        \"knowsAbout\": [\"AI agents\", \"Real estate lead generation\", \"CRM automation\", \"AI agent deployment\"]\n      },\n      \"publisher\": {\n        \"@type\": \"Organization\",\n        \"name\": \"Borstev\",\n        \"url\": \"https:\/\/borstev.com\"\n      },\n      \"datePublished\": \"[YYYY-MM-DD]\",\n      \"dateModified\": \"[YYYY-MM-DD]\",\n      \"mainEntityOfPage\": \"https:\/\/borstev.com\/ai-agent-for-real-estate-5-questions\"\n    },\n    {\n      \"@type\": \"VideoObject\",\n      \"name\": \"Real Estate Automation Is Failing: 5 Questions That Save Your AI Agent\",\n      \"description\": \"88% of AI agents never reach production. If you're about to put AI in front of your real estate leads, these 5 questions decide if yours works.\n\nI learned this the hard way building for real estate - paying for data I couldn't use, watching a fast reply still lose the deal, and seeing how one wrong answer creates a Fair Housing risk. Before any installation, we audit. This is the audit.\n\nIn this video: what your AI agent should NEVER do, where human judgment must stay, why speed without context loses deals, what access and tools it actually needs, and how market shifts kill agents that worked last month.\n\",\n      \"thumbnailUrl\": \"https:\/\/i.ytimg.com\/vi\/HD5qq4di6Os\/maxresdefault.jpg\",\n      \"uploadDate\": \"[YYYY-MM-DDT00:00:00+02:00]\",\n      \"duration\": \"PT[M]M[S]S\",\n      \"embedUrl\": \"https:\/\/www.youtube.com\/embed\/[VIDEO_ID]\",\n      \"contentUrl\": \"https:\/\/www.youtube.com\/watch?v=[VIDEO_ID]\",\n      \"transcript\": \"88% of AI agents never reach production. And if you are about to put AI in front of your real estate leads, that stat should actually scare you. The thing is that it's not that AI fails, it's the process underneath it. Which means that if you don't spend enough time on planning and setup, you're not building an AI agent. You are building the next 88% of useless automations. Let me make it real for you. You've got a lead who filled out a form at 11 p.m. asking about the listing and by the time anyone calls them back, they have already checked a similar house with someone else. And that's the exact moment AI is supposed to fix it. Instant reply, qualify them, get them booked before they go cold. Right? And I know what you're thinking. You have seen the hype. AI will answer every call, book every lead, and give you a massive ROI. But the data says something more interesting and very different. And the answer isn't let the AI do everything because this would be a mistake. It's knowing what to define before you let AI do its job. A while ago, I would have told you that the wrong model and the wrong prompts. So, where does it actually go wrong? For me, there are a few reasons. Based on my work, most clients don't actually know what working really means. They just come to me and say, \"I want an AI then that answers my leads.\" But when I ask them a few questions, they can't tell me what a good answer looks like. So if we build that, the AI agent has nothing to aim at. Second, the client didn't have enough data or couldn't give the agent access to the tools it needed. that the agent only works with what it can actually reach. So if you give it a messy CRM, the data that the agent is going to pull from it is going to be messy one. So it will have to guess which means that the chance of favor is very high. And as I always say, the biggest problem is that most people don't put the border lines at all. They tell the agent, hey, this is what I want to do, but they never tell it like what not to do. And I have made this mistake myself. There is one very recent case where I built one of my own AI agents and I told it what to search for and forgot to tell it like what not to search for. And as a result, I paid for a pile of useless data I couldn't use at all. And actually, the problem wasn't the AI. The AI didn't fail me. It was my fault. I skipped this very important part that matter a lot and I built AI agents for a living and I have watched this happen enough times to know the pattern. So today I will walk you through the five questions that decide whether your real estate business ends up with an agent that actually works or one of the 88% that don't. So let's quickly go through all of them. Question one, what should this agent never do? Of course, often times the instinct when you're building an agent is to describe what you want it to achieve. For example, like find me leads, handle follow-ups, qualify buyers, and then you just let it figure it out how to do all of that. But that's actually backwards. The first question should be, what should it never do? No matter what, say for example, you built an agent to follow up with leads who inquired about a listing. If you only told it, help these leads, it might on its own confirm a showing time, for example, or worse, tell someone a property is still available. But as you know, even inventory changes daily or even hourly. And if that unit went under contract that few hours ago or that morning and your agent confidently tells a buyer, \"Yeah, it is still available. Let's schedule a show up.\" And that's not just an awkward mistake actually. And it can affect the trust and it can potentially lead to a legal problem. So the rule shouldn't be help the lead. The rule is gather interest, answer general questions and never make a commitment. Price, availability, scheduling anything before checking with a human. Start every agent with that. Not with what it should do, but what it must never touch. So you stay away from travel and you increase the chances to deliver what it needs to deliver. Question two, where does your judgment stay? Even once an agent is genuinely accurate, you still need to decide where the judgment stays with you, no matter how good it gets. Because look, AI is smart, but it doesn't have your experience. You know better than anyone which decisions are the riskiest in your business. And those are the ones where you should keep the final call. Because let's say for example that you've got an AI agent which is recommending listings to buyers based on what similar past clients liked. Sounds smart and very interesting but it is actually one of the most dangerous things you can automate because similar clients in historical data isn't neutral. Decades of housing segregation are baked into who bought where. And if the AI starts steering buyers toward or away from neighborhoods based on patterns that quietly correlate with race, that's not a book. That's a Fair Housing Act violation. Nobody typed in anything about race. The AI didn't decide to discriminate. It just found a pattern and optimized for it. And it can be completely accurate and still be illegal. That's why some decisions must stay yours because the license on the line is yours, not the algorithms. So before you build anything, name the decisions you will keep and write them down. Question three, what does working actually look like? There is a trap almost everyone falls into which is I want this to work well. But actually that's not a goal. That's a feeling. And if you can't say precisely what success looks like, you have no way to notice when it stops looking like that. And agents, they drift quietly. And for example, in real estate, some of my clients say, \"But this can mean that the agent needs to reply fast.\" But in reality, in order to give you the best experience and the most ROI, it has to mean something specific. replies within 5 minutes with the right information to correctly tell the buy intent from sale intent at at least 95% of the time and so on. Without that, it can go wrong. For example, the lead comes in, asks for an offer, and of course, the AI answers in five minutes because that's easy, but it doesn't give all the information the client needs. So, they move on to the next agency. So, you're losing this client and everything looks fine on the surface. still replying on time, still sounding helpful, and nobody notices for weeks that it's quietly costing you credibility and deals with every lead it touches. If you can't measure working, you can't catch it when it is breaking. Question four, what does it actually need access to? And this is potentially the most boring question on this list and the one that many people skip most often right before it becomes the reason the whole project stalls. You know what you want the agent to do, but you don't always think through what it actually needs to see in order to get there. Say, for example, your agent is meant to sound like it knows the client. If it can't see the full conversation history, every past call, every past message, it will ask something that was already answered three days ago. And the buyer saying like, \"We told you already we need a fenced yard for the dog.\" And the agent asks about pet policies again like it's the first time. And that's not just inefficient. It is something. It sounds like nobody is paying attention to what the client is saying, which is the last impression you want to give to someone about to make potentially the biggest purchase of their life. So before you build the exciting part, map out exactly what the agent needs to touch, not what you want to accomplish, what it needs access to to even attempt it. Question five, who watches for drift and how often? And it is the one that almost nobody wants to hear because it means that the work doesn't stop after launch. You need to treat your AI agents as a new hire, not a finished product. It needs coaching, correction, time to learn how your business actually runs. And even once it is good, it can still drift. And most probably you won't notice until a client complains or a deal falls through the cracks. And even then it can take time to figure out why this has happened. So for example, imagine an agent trained perfectly for a slow market. Homes sitting 60 days and hurried for a cadence that felt appropriately relaxed. Then the market shifts. Homes start moving in a week and nobody retrains the agent. So it keeps its old SW pace while hot listings fly off the market and leads go cold waiting on a rhythm that used to be fine and now just looks unresponsive. Somebody has to be checking the agent's behavior against current reality on a real schedule weekly or bi-weekly, not whenever something breaks. because by the time something visibly breaks, it's already costing you something. So, these were the five questions. Let's do a quick recap of what we just covered. First question, what should this agent never do? Be precise about what it should never do before you tell it what to do. Two, where does your judgment stay? Name which decisions stay with humans and AI can't touch. Three, what does working actually look like? Give as much detail as possible about what success looks like. Four, what does it actually need access to? Once you know the end goal, make sure the AI has access to the right tools to actually do the job. Five, who watches for a thrift and how often? Set a schedule to check its work so you don't risk your reputation and your clients. This is as exactly the process we run before we ever touch a client's AI agent. We are building, configuring, and maintaining AI agents for real estate businesses. And they can pick up the phone, answer questions, qualify leads, and book them straight into your calendar before that lead goes cold and books a tour with someone else. But before any installation, we do an audit, which means we aim to find the gaps first. the messy CRM, the unanswered calls, the missing followup rules, and then we start asking the needed questions because that's the difference between being in the 12% and being the next 88%. You don't need an AI on top of a broken process. You need one that runs on a process that actually works. And look, I have got a question for you. At the end of this year, check how many of the tools you have paid for are you actually still using. That's the real test, not whether you bought the AI agent, whether you would actually use it every day. And if you want an agent that's built to pass that test, book a call with me by using the link on my profile or the one in the description and let's find out what's already sitting in your business waiting to become more deals.\"\n    },\n    {\n      \"@type\": \"FAQPage\",\n      \"mainEntity\": [\n        {\"@type\":\"Question\",\"name\":\"How many AI agent projects actually fail before reaching production?\",\"acceptedAnswer\":{\"@type\":\"Answer\",\"text\":\"Roughly 88%, according to IDC's research on enterprise AI proofs of concept, a figure independently supported by similar findings from RAND and a Forrester and Anaconda analysis in the 86 to 88% range.\"}},\n        {\"@type\":\"Question\",\"name\":\"Is it legal for an AI agent to recommend listings based on what similar past clients bought?\",\"acceptedAnswer\":{\"@type\":\"Answer\",\"text\":\"It can easily become a Fair Housing Act problem. Historical buying patterns often correlate with race due to decades of housing segregation, so an agent optimizing on similar clients can steer buyers by neighborhood without anyone intending it to. Keep listing recommendations and any judgment call tied to protected classes with a human.\"}},\n        {\"@type\":\"Question\",\"name\":\"What should an AI agent for real estate never do on its own?\",\"acceptedAnswer\":{\"@type\":\"Answer\",\"text\":\"Confirm a showing time, quote a firm price, or state that a property is still available without checking current status with a human first. Its job is to gather interest and answer general questions, not to make commitments.\"}},\n        {\"@type\":\"Question\",\"name\":\"How do I know if my AI agent for real estate is actually working?\",\"acceptedAnswer\":{\"@type\":\"Answer\",\"text\":\"Only if you defined working as a measurable bar before launch, for example a reply time under five minutes with a minimum accuracy rate on identifying buyer versus seller intent. Without a specific target, an agent can look fine on the surface while quietly losing you deals.\"}},\n        {\"@type\":\"Question\",\"name\":\"Do I still need to monitor an AI agent after it launches?\",\"acceptedAnswer\":{\"@type\":\"Answer\",\"text\":\"Yes. Markets shift, and an agent trained for a slow market will keep a slow pace even after listings start moving fast. Someone needs to check its behavior against current conditions on a set schedule, not only after something visibly breaks.\"}}\n      ]\n    }\n  ]\n}\n<\/script>\n\n\n\n<p class=\"wp-block-paragraph\"><\/p>\n","protected":false},"excerpt":{"rendered":"<p>If you are about to put an AI agent for real estate lead follow-up in front of your buyers, one number should stop you before you flip the\u2026<\/p>\n","protected":false},"author":1,"featured_media":0,"comment_status":"closed","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[8],"tags":[],"class_list":["post-31","post","type-post","status-publish","format-standard","hentry","category-real-estate-ai"],"_links":{"self":[{"href":"https:\/\/borstev.com\/blog\/wp-json\/wp\/v2\/posts\/31","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/borstev.com\/blog\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/borstev.com\/blog\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/borstev.com\/blog\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/borstev.com\/blog\/wp-json\/wp\/v2\/comments?post=31"}],"version-history":[{"count":5,"href":"https:\/\/borstev.com\/blog\/wp-json\/wp\/v2\/posts\/31\/revisions"}],"predecessor-version":[{"id":38,"href":"https:\/\/borstev.com\/blog\/wp-json\/wp\/v2\/posts\/31\/revisions\/38"}],"wp:attachment":[{"href":"https:\/\/borstev.com\/blog\/wp-json\/wp\/v2\/media?parent=31"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/borstev.com\/blog\/wp-json\/wp\/v2\/categories?post=31"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/borstev.com\/blog\/wp-json\/wp\/v2\/tags?post=31"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}