13 docs tagged with "context-engineering-studio"

Bootstrap, test, and ship the business context every AI agent needs to produce accurate, trustworthy answers.

Describe your domain in the Context Engineering Studio chat window and let the agent search your Atlan data graph, identify relevant assets, and bootstrap a context repository with a semantic model, skills, and verified queries.

Deploy a context repository in Context Engineering Studio to Databricks Genie. CES pushes descriptions into Unity Catalog, creates one Metric View per table, and configures a Genie Space. On Databricks, deploying is part of the build cycle because Chat and build and Simulate run on the live Genie Space.

Deploy a context repository from Context Engineering Studio to Snowflake Cortex Analyst as a Semantic View. Grant access to your business users, verify the view in Snowflake, and monitor live query traces in the Observe tab.

Enable Context Engineering Studio on your Atlan tenant in Atlan Labs, assign access to your team by enabling the CES flag on a persona, and optionally enable Data Exploration for richer semantic models seeded from query history and BI semantics.

Grant the Unity Catalog and workspace permissions Context Engineering Studio needs to deploy a context repository to Databricks Genie. Required at deploy time. On Databricks, Simulate also runs on a live Genie Space, so simulating requires a first deploy.

Grant the Snowflake permissions Context Engineering Studio needs to deploy a certified context repository to Snowflake Cortex Analyst. Required only at deploy time. You can connect, build, and simulate without them.

Simulations in Context Engineering Studio run autogenerated question sets on your context repository to surface where it answers well, where it misses, and the specific descriptions, joins, filters, or assets to add next.

A Context Engineering Studio repository is built from three primitives: skills (how the agent behaves), knowledge (what it understands), and tools (what it can act on). A reasoning model uses all three together to answer a business question or take an action. Each primitive is a versioned, governed Atlan asset, reusable across repositories and agents.

Find troubleshooting guides for Context Engineering Studio organized by query engine. Covers Snowflake Cortex Analyst setup, Databricks Genie deployment, OAuth, Unity Catalog, Cortex preflight checks, and chat errors.

Resolve common Databricks errors in Context Engineering Studio, including OAuth token failures, Genie Space creation issues, Unity Catalog access errors, Metric View YAML validation, SQL warehouse problems, and chat errors.

Resolve common Snowflake errors in Context Engineering Studio, including preflight check failures, generation errors, YAML validation issues, evaluation timeouts, Cortex Analyst deployment failures, JWT authentication, and chat errors.

Context Engineering Studio (CES) is Atlan's workspace for building, testing, and deploying the business context AI agents need to answer questions accurately. CES generates a context repository (a versioned bundle of skills, knowledge, and tools) from your data catalog, BI lineage, and semantic sources, then deploys it to any MCP-compatible agent, Snowflake Cortex, or Databricks Genie.