Expertise
AI systems that survive the first timeout
Most AI programmes we are asked to look at already have a working demo. What they do not have is a way to score an answer, a permission boundary, or a process that survives a restart. We start with a written rubric and an environment that can run it. Then we build the context store, the memory, the retrieval and the agent, on Databricks, under Unity Catalog.
A feature calls a model. A system is everything that has to be true on the hundredth day.
What we build
- An eval rubric and a test environment before a line of the agent is written
- Context stores and memory that outlive the process
- Retrieval grounded in your own governed data
- Durable execution, so a long job survives a restart
Ways to start
Named engagements, each with a fixed shape.
Accelerators doing the work.
The parts we stopped rebuilding for every agent programme: a durable runtime, an evaluation harness, and a mutation pipeline that treats an agent like any other actor.
A TypeScript framework for durable, deployable autonomous agents.
A Databricks adoption accelerator for quality engineering, experimentation, and governed delivery.
A portable runtime for ontology-based, agent-native business applications.
Durable agents and the console that watches them. Delivered as AI systems, not as a bolt-on to a pipeline job.
How this is delivered
AI systems
Context stores, memory, retrieval and governed agents that survive production.
FAQ
Questions we get asked
Do you build machine learning models?
When the problem needs one. More often the model is not the scarce part. The scarce part is the system around it: where context comes from, who is allowed to touch what, how you know the answer is still right next month. That work is /services/ai-systems.
Can this run without our data leaving our environment?
Yes, and that is the default. Applications and agents run in your workspace under their own service principal, inheriting Unity Catalog permissions. Fabric Harness at /accelerators/fabric-harness is how we deploy that agent as a Databricks App.
How do you prove an agent is working?
An evaluation harness with ground truth you own. Fabric Experiments at /accelerators/fabric-experiments keeps that suite running. When the thing being scored is a Genie space, the named engagement is Genie Accuracy at /databricks/genie-accuracy.
Have you put one into production?
We run our own company on one. GTM Brain is a production Databricks App with durable workflows and human approval gates. Fabric is a commercial product on the same foundation. Across our clientele, delivery work that needed a team of ten now takes three.
Tell us what is stuck.
A technical conversation with a senior engineer. If the honest first step is writing the scoring, we will say so.