Experiments in data and AI.
Projects we build to test ideas before recommending them to anyone else. Each one has an architecture write-up and an honest note on why it exists. They are experiments, not client work.
AI Gateway
One governed gate for every LLM call — models, MCP servers, guardrails, budgets, and audit logs in a single control plane.
Queryline
Plain language in, structured JSON out — one engine that plans, executes, and schema-validates across SQL, NoSQL, and the warehouse.
Knowledge Lens
Every data source in one knowledge base — chat on the left, dynamic views on the right that reshape to each question.
SpecForge
Spec-driven development platform: write the spec, and the platform carries it through to working, reviewable software.
SLM Store
An offline store of small language models that download and run entirely on-device — no network, no data leaving the phone.
Want something like this on your data?
Each experiment maps to work we do for clients: data engineering, AI engineering, and the products on top.