Contact
Tell us what you are trying to do.
Short and specific beats a formal brief. Tell us the problem, the systems it lives in, and what a good outcome looks like. If we are not the right fit, we will say so and point you somewhere better.
Common questions
- Can it run on our own servers?
- Yes. Self-hosting is the default design, not an enterprise upsell. Our platform is deliberately split so that database credentials never leave your network at all.
- Which databases do you support?
- 32 connectors, each its own package — PostgreSQL, MySQL, SQL Server, Oracle, Snowflake, BigQuery, Databricks, Redshift, Trino, MongoDB, DynamoDB, Elasticsearch, Neo4j, Redis, ClickHouse, InfluxDB and the vector stores.
- Which model do you use?
- Whichever fits the job. Everything we build is model-neutral, so you can bring your own key or route to a model running locally.
- Do you take on project work?
- Yes — assessment, implementation and ongoing running. Projects are delivered on top of our own platform, which is why they take weeks rather than quarters.
- How do you start?
- A short call to find the real problem, then a written assessment and a small working prototype on your own data. If the honest answer is that AI does not help here, you will hear that.