The right thing, built well.
We are two builders with product judgment, architecture and engineering in the same heads. We ship AI systems from prototype to production without a hand-off chain, because the people who understand your problem are the people who build it.
Selected work
- 3 wks
- to a speaking prototype
- 2,600+
- children on the platform
- 3 days
- to a working agent
Featured work · Continuous discovery
They needed the product before they knew what it should be.
A voice-AI product
A startup needed to work out what a realtime voice product should be before committing to it. In three weeks they had a speaking prototype with live evaluations; in six, an MVP on scalable cloud infrastructure. Two pilots followed, and they kept us on.
Also
Two more engagements, each a different kind of problem.
Learning the domain
A paper process, no technology team, thousands of children.
A clinical assessment, rebuilt as software
An organisation with no in-house technology function. We learned the clinical domain and turned a paper developmental assessment for young children into a digital tool, handling FERPA-grade data, with the foundation laid so AI features can follow. It is in production today, and its customers pay per child on it.
2,600+children on the platform
Expertise and leadership
Six weeks, six engineers, no working agent.
A working agent in three days, leading their engineers through the build
A security startup’s seven engineers spent six weeks trying and failing to build a conversational agent. We built it with them in three days: the foundation on day one, ourselves; then, with the CTO, we split the remaining work, matching each piece to one of their engineers. By the afternoon of the third day, they demo’d the working app to a major crypto exchange and came away with a preliminary commitment.
3 daysto a working agent
What we build
Agents that work inside your systems
Assistants and automations that take routine work off your team, grounded in your documents, data and tools.
AI inside your product
New capabilities in an existing product, or a new one from the ground up, with evaluations from day one.
A plan and a team that can execute it
Readiness, roadmap and architecture, from people who will still be here to build it.
For small teams
A fractional AI lead or a fixed-scope sprint when you need expertise your own team does not have yet.
Who does the work
The two of us. When you are working out what to build and how, you are working with us directly.
Zach Landes
Engineer, product manager, former economist. First employee at Trumpet, acquired by OpenTable; product leader at Walmart.com; helped architect a $100M ARR metadata platform at Nielsen.
Kevin Juszczyk
Decades of software, data and systems architecture. CTO at Health Decisions, two patents in patient data protection; staff engineer on Nielsen's global metadata platform on AWS.