Ryan Young leads the Young Team, one of Ohio’s top real estate teams. Young Team was founded in 2003 by parents Terry and Jeffrey. Ryan also admits that he often can’t get his agent to call him.
Participate in the INMAN Intel Index Survey
ryan young
But that’s not the problem with a young team. It’s a real estate issue. Teams spend thousands of dollars on marketing platforms that generate engaged leads, then watch those leads trade with competitors because no one follows them.
Young knows this as the CEO and co-founder of Fello, a proptech platform used by nearly 3,000 real estate teams across the country, and as a customer of his own product.
“Fello is great. It generates a significant amount of engagement in my database,” Young said, paraphrasing feedback he’s heard over the years. “So these people are actually listing their homes to our competitors?”
Fello’s answer to this problem is not another voice bot, but Felix, an AI agent that Young calls an “agent operating system” for real estate teams.
Felix autonomously leads calls, texts, and emails, adapts outreach strategies in real-time as new data comes in, hands off qualified leads to human agents, and sometimes stays connected with them.
The product is currently in beta with about 20 teams, and Fello says it plans to make it publicly available within the next 30 days.
“Why don’t you call me instead?”
Fello launched in 2021 as a direct-to-consumer iBuying concept and was originally called FlashHouse. Around the same time, as interest rates started rising, Young said they realized iBuying wasn’t scalable for them.
“In October 2022, we quickly pivoted to a SaaS subscription-based model and sold our platform to distributors nationwide,” Young said. “Agents sync their database to our platform and we market seller messages on their behalf. We get home prices, we get cash offers.”
The model grew rapidly. Young said the company currently has about 3,000 real estate teams on its platform and about 40,000 users.
“What’s interesting over the last three years is that we’ve done a great job of creating engagement through email marketing into a database of these people that is actually very dormant, very quiet, just kind of sleepy,” Young said. “And we woke them up, right? A lot of the involvement in the database is primarily on the seller side.”
But Ferro had a problem. Many of our customers said they love the platform and it generates engagement. But then an attractive prospect listed a partnership with a competitor. Fello’s customers were unable to call agents and have them consistently reach out to these leads.
“I’ve heard this feedback so often over the last few years that I joked, ‘Do you just want us to call you?'” Young says. “And to be honest, we finally realized that there might be a way to do just that.”
Felix took the joke seriously and responded. The AI agent ingests Fello’s underlying contact data (real estate ownership history, stock position, mortgage type, AVM quote, MLS activity) and builds an automated outreach strategy for each contact. Your strategy will automatically update as your contact status changes.
The demo Young gave Inman explained its peculiarities.
In one case, Felix discovered that a contact had recently purchased a new property while still owning the home they had owned since 2003. Felix sent a text that referenced both properties by address, and the prospect was interested. Within hours, Felix called him and transferred the conversation to Young’s team as a live listing appointment.
Adjust your strategy in real time
Tom Schrader, Fello’s co-founder and chief product officer, says it’s not the voice that separates Felix from the wave of AI calling tools hitting the market, but the connective tissue underneath.
“There’s no one to call anyway, so the fact of just calling is not even there,” Schroeder said. “It’s important to get results without effort.”
During the setup process, Felix scrapes real estate agent websites to understand the market and agents begin their outreach without setting scripts, cadences, or triggers. Schroeder said Felix works with contacts over months or years, adjusting strategies as signals of intent change.
One example Young gave is of a prospect who mentioned using his 401(k) for a down payment during a call with Felix. Felix then wrote and sent a personalized email outlining a 401(k) withdrawal strategy for homebuyers, written not from a template but in the context of that specific conversation, Young said.
“People look at this and say, how did you create a template for a 401(k)?” Young said. “I feel like there’s no such thing as a template.” In other words, Felix was customizing the email in real time to fit the scenario.
A very important handover to human agents
The handoff from Felix to a human real estate agent is some of the products Fello is most focused on getting right.
Once most AI calling tools qualify a lead, they will try to put the prospect on hold and transfer it to a human agent. It’s a process that creates about 70% turnover by the time an agent arrives, according to Young.
Instead, Felix continues a live conversation with the prospect while simultaneously briefing the agent on a separate line, acting as a bridge between the two sides once the human real estate agent is sure they are ready.
Young’s team received 30 handoffs in one Monday during the beta period, he said. The platform’s notifications dashboard showed handoffs arriving every few minutes in real time during the demo.
“You’re focusing on the bottom of the funnel, not the top of the funnel,” Schroeder says. “And that’s all you have to focus on.”
When it comes to compliance, Fello uses your existing email platform to obtain TCPA-compliant consent before Felix initiates a call or text message. Schrader said the company built its own consent tools rather than using a third-party service.
Felix has also been scrubbed against the Do Not Call registry, and the platform has state-specific settings for two-way consent requirements and disclosure of prerecorded calls.
“Have you ever seen the movie ‘Her’?”
Making it sound like a human voice required more than replacing the premium text-to-speech engine. Schroeder said Ferro overlays its own prompts and what he calls “disfluency engineering” — intentional pauses, hesitations, and intonation cues — onto third-party speech engines, including Eleven Labs.
“We’re focusing on how to get better intonation, better emotion, better pauses. We need to introduce natural inconsistencies in the rhythm of speech to humanize it,” Schrader said. “It doesn’t just happen unintentionally.”
Schroeder joked that as founders, he and Young were understandably very “obsessive” about getting things right. “We looked in great detail at all the little things that make us human,” Schroeder said.
In one of Young’s demo calls, two separate prospects told Felix mid-conversation that they thought they were talking to a real person. The two continued their conversation even after being told that they were actually talking to an AI agent.
On one of the calls, the prospect hung up after about a minute and said, “Hey, I’m going to talk to you. “It looks like I’m talking to a real person, but I think it might be an AI call. Am I talking to a real person now?”
Felix says, “Oh, you got me. Yeah, I’m actually a digital assistant on the Young Team, so you’re talking to an AI, and it’s a very friendly AI. I’m here to help start the conversation, gather some information, and connect you with a human expert who can dig into the details. Will that work, or would you prefer to have a real person call you back directly?”
The prospect sounded less annoyed and more impressed, saying, “This is one of the most sophisticated AIs I’ve ever talked to. For a moment, I thought I was talking to a real human.”
In another call to Inman during the demo, the prospect said, “Can I talk to you for a second? If you had told me you were a real person, I would have believed you.”
The Felix AI agent answered confidently: “Honestly, I think that’s a huge compliment. I know I’m digitally savvy, but I try to make things feel natural and actually useful. [That] I had a lot of fun today. ”
The prospect replied, “Even if you’re not real.”
Felix immediately responded, “Hey, I’m serious enough to have this conversation with you. But seriously, do you want someone to contact you about that evaluation question, or are you pretty happy with the way things are?”
Listen to the call below
Of course, not everyone wants to talk to a bot. But Young’s answer to that objection is call length.
“These calls aren’t just one or two minutes. Some prospects are talking to the AI for 15 to 20 minutes, and the reason for that is context,” Young says. “We built our platform on rich data about home equity, mortgage types, properties owned, etc. So when the AI reaches out to you, it’s not a telemarketing call. It has enough information to have a really meaningful conversation.”
The adoption of AI voice is rapidly accelerating. Some people still feel uneasy when talking to AI due to the “uncanny valley” effect, where they hear sounds similar to but different from humans. But familiarity wins out. Millions of consumers grew up talking to Siri and Alexa, but are now increasingly relying on voice modes built into ChatGPT, Claude, and other AI platforms.
“Have you seen the movie ‘Her’? I think this is the direction our world is headed,” Young said. “I think people are actually starting to like talking to AI.”
“I can’t imagine going back to the old ways.”
Young said Felix set a timeline for the team to list about 60 people during the 90-day beta period. The young team uses the Felix product and serves as a live lab to test and improve it.
Young repeatedly compares it to other AI calling products. This is the inside sales associate model that many top teams have built their operations around.
“You can’t train an ISA or an agent in 90 days,” Young said. “I’ve had an ISA for a year, and they still don’t know about the homes we’ve sold in the past. Felix knows all that stuff and knows it right away. There’s no need to fire Felix and then rehire a new ISA.”
But Young continued. “Here’s the scary part. It’s great for Ferro. It’s scary for our industry. We can’t imagine going back to the old ways.”
Young said if he lost Felix, he would suddenly have to make his agents and ISAs responsible for every phone call and text message Felix made.
“The biggest challenge our industry has is that we’re not very strong managers. We’re sales people, and we’re growing big companies,” Young said. “And we’re having a hard time creating consistent processes. And there’s a lack of accountability.”
Most real estate professionals “want to go out and sell, and we struggle to stay disciplined,” Young said.
“So we have a vision of how we look at the future of this agent, what’s going on in the world, what’s happening, and ultimately build this agent operating system that helps them be consistent with their operations so they can sell their homes and do what they love,” Young said.
Email Nick Pipitone
