Leaping AI

AI agents that call and text in multi-day campaigns

Artificial Intelligence

Home improvement

Visit WebsiteSee on Product HuntTwitter ⧉

Missed calls and slow speed-to-lead are massive pain for local service businesses, banks especially lol. Putting appointment scheduling and confirmations on autopilot with multi-day campaigns is a game-changer for trades. Congrats on the launch, goated!

Congrats on the launch! Multi-day AI campaigns are an interesting approach. How do you measure success across longer customer journeys compared to traditional outreach?

multi-day is the part that sounds small and is not. a campaign running for weeks means the agent's picture of a contact has to survive between sessions, and every stale field is a chance to say something that was true last tuesday.

the thing i would want measured is the gap between "we placed the call" and "a human heard it". we work on an adjacent problem, confirming a form submission actually registered on someone else's system, and the honest version needed independent confirmation rather than our own send log. voicemail, a carrier drop, and someone who hung up in two seconds all look like a completed attempt from the sender's side.

how are you counting those?

The "similar to HubSpot sequencing but for calls/texts" framing makes total sense, and the channel-agnostic DNC record (spoken stop = texted STOP) is the kind of detail most teams skip until it bites them. We deal with a version of this on the WhatsApp/email side, once someone's mid-conversation with our AI and a human needs to step in, we keep the same thread going so there's no "starting over" moment.

Curious how the handoff feels on your end when a homeowner insists on a real person mid-call, does the human rep see the full call history instantly, or is there a summary step first?

Leaping has come so far from its first launch! What challenges did you have to solve to maintain context and memory across these channels?

That's interesting. When a homeowner insists on a real person, how does the handoff actually work?

Kevin, the multi-day campaign is the part I would stress test, and it is not the dialing. You covered opt in and STOP over SMS, which is more than most voice products say out loud. What I would check is the spoken revocation.

If someone tells the agent on day 7 to stop calling, that counts even though it never touched your SMS keyword path, and it has to end the remaining calls and the texts. I work in a regulated space where consent is tracked per channel, and the failure always has the same shape: the person revokes on the channel in front of them and the sequence keeps running on the other one.

Does a spoken stop write to the same DNC record as a texted STOP, and does it close the whole campaign or only the call leg?

The horizontal to home remodeling niche-down is a smart call, the physical-world trades are so underserved by voice AI. I work on the consumer side (daily check-in calls to aging parents), and the thing that quietly kills outbound for us is carrier spam labeling: even a wanted, friendly call gets flagged "Scam Likely" and never picked up. With 100+ parallel outbound calls, how are you handling number reputation and STIR/SHAKEN attestation so calls actually connect? Would love to hear what held up at scale.

Hey ProductHunt!

I am Kevin, maker at Leaping AI.

Today we are launching our AI voice and texting platform, specifically for home remodeling companies. We started originally as a horizontal voice AI calling platform and have gradually niched down to the home remodeling industry.

Why? We signed up our first home remodeling companies because they approached us inbound via our website and we discovered that they have a list of specific pain points that makes our voice AI solution almost a no-brainer.

Pain points that we address

Home remodeling companies miss calls on the weekend or after-hours because no one is in the office, struggle to reach out to web leads fast enough over the phone and therefore lose leads to competitors, cannot serve Spanish speaking customers because usually no on on the team speaks Spanish and cannot (at scale) reactivate old leads that didn't buy in the past but might now be interested again.

Our solution

Our solution is AI agents that can take inbound phone calls and make outbound dials, specifically to schedule appointments and confirm appointments. They can hold 100+ conversations in parallel, are always active and stick to the script (a big problem in the industry). We can deploy both English and Spanish speaking agents. Inbound leads are being reached out to in under 10 seconds.

If leads do not pick up, our AI texting agents will send them a text message and follow the same conversation flow.

Our differentiator

Something that differentiates us is that the AI calling and texting agents can now be weaved together in multi-threaded campaigns. It's similar to sales software, like HubSpot, where you can create multi-day sequencing with email sequences mixed together with LinkedIn outreach and cold calling. In our platform, our customers can create similar campaigns where new leads, that have opted in to be reached out to (strict requirement), will be contacted via calling and texting until they pick up and schedule an appointment. Leads can at all times opt out of these campaigns by texting STOP via SMS. We maintain our own DNC database and strictly respect that.

It can be configured how long the campaigns last, what the exit conditions are and also what the cadence should be (e.g., how many calls and texts on day 7 vs. day 14 of the campaign). Home remodeling companies already have a similar process in place with humans and now our AI agents can complement that team and provide more firepower.

We have been live with this already with several large brands in the space, e.g. Bath Experts, Aspen Contracting, etc.

Our ask

Please give us feedback on our solution and what features we should build next. We are constantly iterating and are always open for new inspiration.