Quiet systems, measurable outcomes.

What we're building in production right now, across property, hospitality, trades, and professional services. Anonymized where clients asked. Still running.

Results: Systems we've shipped

In production now, anonymized where clients asked. Detailed case studies are shared under NDA on request during a discovery call.

Flagship 01: Voice agents that never miss a call (property management and brokerage)

Inbound calls were slipping to voicemail after hours and during busy stretches. Lina and Maya now answer every inbound call, understand what the caller needs, and either handle it, route it to the right person, or write the lead straight into the CRM, by the rules the operator sets.

Verified numbers from live deployments:

  • 0 calls missed
  • ~600 calls answered a month
  • 27% after hours or on weekends
  • 7 in 10 brokerage calls leave a lead

What it looks like in the pipeline

Across a two week window (July 8 to July 22, 2026), 130 new leads were created in the client's CRM. 34 of them, 26%, came in through the voice agent. That made it the second largest source of new business, behind only the biggest listing portal, and ahead of the next two portals combined. Client anonymized; the agent's leads arrive under two source labels in the CRM and are counted together.

More at [/voice-agents](/voice-agents).

Flagship 02: A booking platform that replaces the middleman (hospitality and short term rental)

Every reservation arrived through a listing marketplace that took a cut of it, owned the guest relationship, and set the rules. The operator had no direct channel of their own.

We built a complete platform, front end and back end: a booking engine and checkout that takes reservations directly, an operator portal for the team, a guest portal for the stay, bilingual throughout, and live local data that refreshes on its own rather than going stale.

What shipped:

  • Booking engine and checkout
  • Operator portal and guest portal
  • Bilingual, English and Spanish
  • Self refreshing local data

Most bookings now come in direct rather than through the listing sites, so the platform fee stays with the operator instead of the marketplace.

Also in production

  • Search traffic that stopped being guesswork (online platform). Pages were being written on instinct, with no way to say which searches the site was competing for. We mapped and sized real search demand, built a page and content architecture around that map, added on page data that updates itself, and did answer engine work so ChatGPT, Claude and Perplexity can find the site and quote it correctly. Outcome: every page now aims at demand the team can name, and they watch performance in a dashboard that syncs itself daily rather than waiting on a monthly report.
  • A CRM built around how a trades business actually runs (trades and home services). Tracks every lead from first call to paid invoice: jobs, quotes, scheduling, and follow-ups in one place. Outcome: fewer dropped leads, faster quotes, a clear view of the pipeline.
  • Books that keep themselves (operations and finance). An automated accounting pipeline that pulls transactions, categorizes and reconciles them, and produces the reports the business actually reads, with a human checkpoint where it counts. Outcome: reconciliation that used to take days, handled quietly in the background.
  • The busywork, automated (across the business). Automations across sales, marketing, and operations that move data, trigger the right follow-up, and keep systems in sync. Outcome: hours back every week, spent on the work that needs a person.