A growing number of proptech companies are racing to incorporate AI into everything from CRMs to marketing platforms. But one startup is taking a different approach. Instead of building another feature, we want to be on top of the entire stack.
BrokerBot positions itself as a brokerage-wide AI assistant designed to work across systems, not just within a single system. CEO and co-founder Jerimiah Taylor says the goal is to create a tool that behaves more like a digital team member than a chatbot, answering questions, performing tasks, and coordinating deals from start to finish.
The idea was born out of a pain point that intermediaries are familiar with. Agents are constantly looking to brokers for guidance on edge-case scenarios buried in contracts, compliance rules, and documents. BrokerBot was originally designed to absorb that organizational knowledge and make it instantly accessible. But Taylor said the platform quickly evolved to go beyond just answering questions and running multi-step workflows.
In one example, a system can read real estate contracts, extract important dates, generate calendar reminders, draft emails, enter contacts into a CRM, and flag missing information all before a human ever looks at the file.
“This is where we’re going from here,” Taylor told Inman, referring to the future of AI in real estate. “The machine becomes the transaction coordinator.”
The Rise of “Agent Operating Systems”
Unlike many AI tools that are built into existing platforms, BrokerBot is designed to work independently and connect across systems. Taylor said the company is building integrations with tools like Google Calendar, Gmail, Outlook, Canva, Close, and Follow Up Boss, allowing the assistant to move between workflows just like human staff.
“What we’re seeing is everyone else has gone out,” he said. “We are building the most sophisticated standalone AI agent in existence in this space.”
The company says it already works with 240 brokerages and approximately 24,000 agents, and recently entered into a national partnership with Keller Williams Realty International to integrate BrokerBot into its command platform.
This positioning reflects recent changes in proptech AI. Rather than relying on a single large language model or single platform, many proptech companies, including Breezy and Homie, are building “real estate agent operating systems” that combine multiple models, proprietary data, and workflow integration into one system.
Speed and simplicity drive adoption
BrokerBot uses an internal benchmarking system called “BrokerBench” to evaluate how different AI models perform on real estate-specific tasks such as contract analysis and licensing exam questions.
Based on these results, the system can route tasks to the best performing model instead of relying entirely on a single generic model. Mr Taylor said this was particularly important in areas such as contract extraction, where errors or omissions could carry real liability.
“Some models like ChatGPT miss a lot of things,” he said, noting that performance varies greatly depending on the complexity of the form.
The platform also builds a privilege-based knowledge system that blends intermediary documents, vetted web sources, and user-specific context. This allows agents to adapt responses based on geography, MLS rules, and brokerage policies without having to manually enter that context each time.
Although the backend architecture is complex, Taylor said the product’s success ultimately depends on simplicity at the user level. He said real estate agents are less concerned with how the system works and more focused on immediate results.
“What they care about is being able to ask for something and get what they asked for in real time,” Taylor said.
As AI expands, so too will surveillance.
As AI tools expand into more parts of trading, regulatory considerations are becoming increasingly important, Taylor said.
This year, California became the first state to establish clear standards to allow the use of AI in real estate marketing through Assembly Bill 723.
The law, which took effect on January 1, requires that real estate images that have been “digitally altered” be clearly disclosed in the context of advertising or promotions, and that the original, unedited versions must also be made public. In practice, this means that if the room is virtually staged, the listing should label the image as modified and include the unstaged photo next to it.
“What’s going to happen is that a lot of companies that are building AI systems in real estate are going to have to require hard timeouts and build more robust guardrails,” Taylor said. This dynamic could shape the next phase of proptech AI, where compliance infrastructure becomes as important as raw functionality.
What Disneyland Reveals About the Future of Agents
Rather than replacing agents, Taylor believes AI has the potential to push them into more advanced, experiential roles, akin to high-touch concierge services. He explains this change with an unexpected analogy: Disneyland.
Taylor points to Disney’s premium guided experiences, where guests can pay thousands of dollars to have a dedicated staff member guide them around the park, skip lines, and adjust their day in real time.
“They give you a guide and walk you around and get you to the front of every line,” Taylor explained. “I call it ‘human fastpass.’ People pay for an experience because it’s an experience.”
As AI tools take over repetitive, rule-based tasks in real estate, agents’ traditional responsibilities are being separated. What remains, Taylor suggests, are aspects of human perception, intuition, and emotional intelligence that technology still struggles to replicate.
“That person is curating your trip,” he said, referring to the Disneyland guide. “They explain things to you along the way. They watch what you’re doing and if you look a little hungry, they order churros.”
In real estate parlance, that means anticipating client needs before they are manifest, reading subtle cues during viewings and negotiations, and connecting insights not easily captured by data.
This is not just a change in responsibilities, but a redefinition of values. In a world where AI can accelerate transactions and reduce friction, speed will no longer be a differentiator. Experience becomes the product.
“Really astute real estate agents have the opportunity to become curators of the experience, and by leveraging machines to their advantage, they can significantly speed up their work and spend more time on the experience than the transaction,” Taylor said.
If Taylor’s vision of the future holds true, tomorrow’s real estate agent might look less like a dealmaker and more like a guide, someone who knows when to intervene, what to say, and sometimes when to order a metaphorical churro.
Email Nick Pipitone
