Roadmap

Investing in the core of AI Analyst for better reliability, and for improved enterprise readiness.

Fine-grained role and permission controls — separate tenant admin, Studio, and Explorer roles with asset-level access scoping per user or team.

Let enterprises bring their own LLM (e.g. Azure OpenAI, AWS Bedrock) so AI Analyst runs entirely within their own infrastructure and data governance boundaries.

Enable enterprise single sign-on via OAuth 2.0 / OIDC so teams can authenticate with their existing identity provider (Okta, Azure AD, Google Workspace, etc.).

Automate user lifecycle management (create, update, deactivate) via SCIM, eliminating manual onboarding and laying the foundation for role-based access.

Automated benchmarking framework to track AI Analyst quality and catch regressions on every change.

Allow users to interact with AI Analysts via Google Workspace Chat (1:1 and space-based conversations)

Define row-level access rules in the semantic layer so users only see the data they're authorized to query.

Connect external MCP tools (Slack, GitHub, Linear, etc.) to the Steward agent to extend its capabilities.

Separate staging and production environments in Studio for safe testing before promoting changes to live.