Property software engineering capabilities
Bookings, crews, channels and roles, and how AI has to fit them.
AI in property operations only works when it acts with each person's own rights and reaches crews where they are. These are the systems we have worked with and how the team works.
The team
Who builds it.
Product and workflow analysis
Business analysts who map each role's day, from booking to turnover to repair, and analyze screens such as the calendar before any code.
AI engineering
Agents with tools on your own APIs, a tool list per role and channel, voice and text channels, and evals in tiers.
Platform and mobile engineering
Serverless backends, logins and roles, and React Native apps with push actions, deep links and builds per environment.
Data engineering
Property and unit data collected and structured, schemas for properties, units and media, and listing feeds.
Systems
Systems we have worked with.
Built in client products. We scope yours in the Product Review.
| Area | Systems |
|---|---|
| Backend and logins | AWS API Gateway and Lambda, Cognito sign-in through Amplify, Google and Apple sign-in |
| Messaging and voice | Twilio text and picture messages on a short code, Stream Chat channels, Slack in Socket Mode, LiveKit voice on OpenAI realtime models |
| Agents and evaluation | LangGraph with a Postgres checkpointer, the AG-UI protocol, LangSmith traces and evals, Qdrant for property documents |
| Mobile | React Native with Expo, EAS builds per environment, TestFlight, push notifications and deep links |
| Email, storage and logs | Amazon SES, SNS and S3, CloudWatch logs |
| Listings | Next.js and Supabase with Supabase Auth, Mailgun, CSV data deliveries and an XML rental listings feed |
How the team works
One team across product, AI, platform and data.
A named lead engineer and US-hours overlap, from the first Product Review to production.
Every engagement
- We add AI through your existing APIs and logins, and put anything new into your own backend by pull request.
- Every change goes through your pull request review, with separate development and production environments.
- We share demos as features land and take designs to your team before we build.
- We work in your AWS accounts, with access you grant and can revoke.
See it on your own platform.
Bring one product, workflow or AI feature. In 30 minutes we tell you which of the three ways to start fits, what it would cost to serve per property and what your customers will ask about permissions.
Calls run in US Central time. No generic AI presentation: we discuss your product, users and production constraints.