Internal tools and line-of-business apps, built on infrastructure you own
When the off-the-shelf tool almost fits, the gap is usually a small application: a portal, a scheduler, an approvals screen, an internal dashboard with AI where it helps. We build those as ordinary web applications, with source code and documentation handed to you, on servers and databases in your name.
What we build
- Web applications and internal tools with a Node backend and a PostgreSQL database
- AI features designed in where they earn their place: drafting, classification, extraction, search
- Integrations with the systems the tool has to read from and write to
- Deployment to infrastructure you own, with a documented way to run it without us
What you keep
- The source code, the deployment guide and the admin guide
- Architecture and database documentation
- A security checklist and the maintenance procedures
Where it shows up
- Trades and home services
- A customer portal for quotes, scheduling and invoices that talks to the system you already dispatch from
- Professional services
- A client intake and document-request tracker that replaces the shared inbox
- Churches and nonprofits
- A volunteer and events hub with sign-ups, reminders and the reports the office needs
Try a small version
A working example running in your browser. The real thing runs against your systems, on your infrastructure.
AI Quote Generator
Generate inspiring quotes by topic
Popular topics:
Demo uses pre-defined quotes. Production systems generate unique content via AI.
Guardrails
We treat an agent that can act as a production system, because it is one. Every agent we deploy has these four things.
- Defined task boundaries
An agent does the job it was built for and nothing adjacent. The boundary is written down before it runs.
- An audit log
Every action the agent took, with what it saw and what it decided, in a log you can read.
- A human approval step
Anything that touches money or customer records waits for a person to say yes.
- A rollback path
If it goes wrong, there is a known way back, tested before launch, not improvised after.
Related work
Integration and MCP
AI connected to the systems you already run: CRM, accounting, scheduling, email
Learn moreBack-office automation
The repeatable work done without a person retyping it
Learn moreAI cost management
Usage instrumented and spend controlled, treated like cloud cost rather than an afterthought
Learn more