👋 Hi, it’s Kyle Poyar and welcome to Growth Unhinged, my weekly newsletter exploring the hidden playbooks behind the fastest-growing startups.

I’ve been fascinated by emerging AI use cases for go-to-market. Folks are vibe coding ROI calculators, quickly spinning up lead magnets, hiring AI agents for marketing, and running signal-based GTM plays. The use cases are endless, and a bunch of fun.

But very few are suggesting AI as a replacement for salespeople. Remember, for example, how Salesforce said they’re actually hiring 2,000 more salespeople to sell AI?

Well, there’s an outlier: Adam Robinson, the outspoken founder and CEO of RB2B, which helps de-anonymize website traffic to convert them into high-value leads. Adam has grown RB2B to $5.5M ARR with three people (down from five at the beginning of June). His goal is to bootstrap to $10M ARR as profitably as humanly possible.

Adam recently ran an experiment to replace RB2B’s two person sales-assist team with a $99 per month AI avatar trained to respond to inbound requests from prospects. The AI avatar, which is also a clone of Adam, had 1,683 (!) conversations in its first 22 days, and with surprisingly good answers. I sat down with Adam to get the full unfiltered story of what happened.

Meet the Adam Clone. It’s an AI avatar that lives on the public-facing side of RB2B’s website, designed to handle what a sales-assist rep would normally do: respond to inbound interest, answer common questions, and move people toward purchase. Think of it as an AI-powered “Contact Sales” button available 24x7 without the two-day wait for a reply.

This is distinctly not customer support chat. Adam draws a hard line: once someone becomes a customer, they interact with Fin (Intercom’s AI, profiled earlier), which is better suited for RB2B’s troubleshooting and post-sale help. The Adam Clone was made with Delphi and exists purely to accelerate new sales conversations, especially for the prospects who already have an affinity for Adam through his LinkedIn #influencer content.

So what does the avatar actually handle? 90% of what buyers ask falls into six topics:

Here’s an example of what this looks like in practice:

In the first three weeks, the AI avatar handled 304 demo requests, 98 SOC2 docs, and 16 custom pricing quotes. (As an aside, it can’t actually deliver a demo yet. The avatar currently sends people to a pre-recorded demo video on YouTube. Adam would love to see the AI avatar ask qualifying questions, then personalize the demo experience for each prospect.)

RB2B’s growth motion starts with Adam’s LinkedIn content to feed top-of-funnel. They convert prospects with a freemium, product-led experience. And they offer a layer of sales-assist for higher-touch prospects.

Under the hood, things were breaking down. “We thought we had an enterprise motion,” Adam told me. “Turns out, we didn’t.”

RB2B initially tried to go upmarket, chasing bigger logos with more traditional sales cycles. But it quickly became clear that others were better suited to serve that segment. RB2B lost or churned most of those deals.

Instead of forcing an enterprise motion that wasn’t working, Adam refocused on a different goal: make it dead simple for anyone to start using RB2B. That meant building for speed and self-serve conversion.

Sales-assist was supposed to help with that. But even that didn’t hold up to scrutiny. “We kept asking: is sales-assist actually incremental? And there was no convincing data that it was.”

So Adam made a provocative bet to remove the human sales-assist role and replace it with a bot. To be clear, this is part of Adam’s ethos. He believes a lot of founders should have a goal of hitting $10M ARR with as few people as possible. “If you can get there, you can do whatever you want with your life,” he said.

RB2B had previously placed an early bet on Fin (Intercom’s AI), and while it flopped at first, it’s now 5x better than it was 18 months ago and successfully resolves 75% of support requests. Combine that with a high-volume funnel – 80 signups a day, 10–15% converting at $149/month — and the downside of getting a few interactions wrong was fairly low.

It’s worth contrasting this with the approach taken by Calendly, which I profiled last year. Calendly went the route of investing significant time and money into sophisticated lead qualification and routing, sending prospects to a combination of on-demand demos, the sales-assist team, velocity sales, or enterprise sales. While their results were great, the level of complexity involved doesn’t necessarily make sense for a three-person business like RB2B.