Compass has been showcasing a conversational AI demo that turns everyday agent tasks into a seamless, voice-driven workflow. Every broker should aim to stay ahead or keep up with Compass. This means owning your AI platform, and owning your data. We call this AI Soverenty and it’s the keynote of how WAV Group’s AI Division – Fluente – is coaching and building AI for brokers. When you work with us, you own your AI, not rent it.
At first glance, it looks like magic: the agent asks a question, the AI responds, and business moves forward. But behind the scenes, what’s really happening is a carefully orchestrated sequence of MCP server calls, CRM API integrations, and MLS property data connections. We build all of this stuff, your technology team can too. Sometimes brokers and their tech team need a coach, or someone to jump in and get it done. Fluente does both.
Let’s break down the Compass demo step by step — and discuss how brokerages can match (or surpass) this type of experience.
What to learn:
- Brokerages with Office 365 or Google plugins could replicate this with integrations between the broker’s AI experience and a connection to calendar.
- The voice interaction here is excellent.
Step 2: Birthday Reminders & CRM Notes
Agent asks: “Do I have any clients with birthdays this month? If so, put a note in my CRM to reach out and tag my assistant Jed.”
Here the AI is searching customer records for birthdays, creating reminders, and assigning tasks. Compass again leans on Contactually for CRM API integration. But this is where third-party data enhancement services like Aidentified can play an even bigger role. These platforms can automatically match the customer records and append missing birthdays, anniversaries, or even life events to contact records.
What to learn:
- AI shouldn’t create more work for agents — it should do the work. That means not just logging tasks, but also triggering the birthday text, card, or gift order.
- Brokerages can differentiate by integrating AI with gifting platforms (e.g. Evabot), so an agent can say, “Send Michael a gift for his birthday,” and it just happens.
Step 3: Preparing for a Client Meeting
Agent asks: “I’m meeting with Jacob Wells. Can you remind me of his preferences and pull some market stats for the West Village? Draft me an email I can send him.”
This CRM task is the most complex part of the demo. To deliver, the AI must:
- Retrieve Jacob’s saved searches or property cart.
- Recall his buying criteria (2-bedroom, 2-bath, price range, neighborhood).
- Query MLS or brokerage search tools for updated listings.
- Generate market stats (price trends, days on market, absorption rates).
- Design the report
- Draft a client-ready email.
Compass positions its CRM as the hub for saved searches, but brokerages have multiple options here. MLS client portals like OneHome (Cotality), point solutions like CloudCMA, or native brokerage tools. The real magic is in the orchestration: the MCP server routes the queries to each data source and brings the results back to the AI conversation.
What to learn:
- Don’t stop at generating a “market update email.” AI should guide the agent: “Jacob currently owns a condo at 123 Main Street. Do you want me to draft a CMA for that property as well, in case he needs to sell before buying?”
- AI connectors for CMA and Market Stats are essential. If MLSs and vendors don’t expose APIs for these workflows, their tools risk being sidelined. In the case of CloudCMA – the job can be sent from the MCP server to CloudCMA via API, email, or text message and the report is generated and returned. This was a key selling point of CloudCMA when this functionality was released in 2014.
The Bigger Picture: Why MCP Servers Matter
Compass’ demo makes one thing clear: the future of brokerage AI depends on seamless connections between CRMs, MLS systems, productivity suites, and third-party data services. That orchestration happens through MCP servers, a middleware orchestrator that translates a conversational request into discrete jobs routed to the right endpoints and specialty AI agents.
If MLSs and brokerages don’t provide MCP access, agents and vendors will start replicating data to power these workflows themselves. That’s a slippery slope, leading to loss of data oversight and poor governance. The smarter move is for brokerages and MLSs to own the orchestration layer and maintain sovereignty over their AI strategy, data assets, and agent access.
Final Takeaway
The Compass AI demo is impressive, but it’s not unattainable. Brokerages can match or exceed it today by:
- Integrating calendars, CRMs, and MLS portals through MCP servers.
- Using data enrichment tools like Aidentified to keep customer records fresh.
- Embedding AI connectors into core MLS and vendor tools (CMA, market stats, gifting).
- Focusing on work completed, not work delegated — ensuring AI takes tasks off the agent’s plate instead of just creating more reminders.
The timing is important too. Compass anticipates rollout of this functionality this fall to a limited group. Top producing agents and teams are hungry for this automation. WAV Group anticipates that Compass will have a compelling technology narrative for recruiting and retention when this AI platform releases. It may be somewhat limited at first, and that is important too. You cannot throw too much tech at real estate agents at once, or the adoption task becomes overwhelming.
Get in the game with a few AI features that have an impact for agents. Monitor the market for features that are attracting agent buzz. Reinforce that your AI strategy is solid. The lesson for brokerages is clear: owning the AI orchestration layer is how you future-proof your business and create experiences that Compass is previewing here. The stakes are high.
WAV Group is not just helping with AI education and strategy for brokerages and MLSs, we are building it through Fluente, our wholly owned AI subsidiary. Fill out the contact form below to discuss ways to collaborate on your AI solution.
More WAV Group Reading
WAV Group white papers, articles, and videos on the evolution of AI in real estate. Reach out below if you would like to learn more about our Tech and AI services.
Leave A Comment