Context Engineering Studio Private Preview
Context Engineering Studio (CES) is Atlan's environment for building, testing, and deploying the business context that AI agents need to answer questions accurately. Business context (how your company defines revenue, churn, active users, or any other metric) is typically scattered across dashboards, SQL queries, data models, and tribal knowledge. CES reads your enterprise data graph in Atlan and bootstraps a semantic model from that existing knowledge, so you're not starting from scratch.
The output is a context repository: a versioned, domain-scoped unit of context that domain experts can refine, simulate with a question set, certify, and deploy. One certified repository deploys to every AI agent that needs it, with one definition and consistent answers everywhere.
Core capabilities
Context bootstrapping
Business context is scattered across dashboards, SQL queries, and tribal knowledge. CES reads your enterprise data graph and generates a context repository with metrics, filters, relationships, and instructions in minutes.
Evaluation and testing
Without a way to see where your model answers well and where it falls short, you can't stand behind a release. CES runs evaluations, surfaces specific gaps, and recommends fixes so domain experts can certify with confidence.
Deployment and observability
One certified context repository deploys to Snowflake Cortex Analyst, Databricks Genie, and MCP-compatible clients. No rebuilding context per platform. Monitor live queries and iterate from production feedback.
Get started
Follow the steps below to start using Context Engineering Studio.
Enable
Enable CES on your tenant, assign access to your team, and connect your query engine.
Build
Describe your domain, generate a semantic model, refine definitions, and simulate with a question set to see where to improve.
Deploy
Certify your context repository and deploy it to Snowflake Cortex Analyst or Databricks Genie.