A portable decision layer for data automation, so agents can make smarter decisions.
MCP-based tools for adding any type of context to data workflows. Author policies, set conditions, enrich tables, validate uses, and expose that context for agents.
Business logic, data contracts, policies, lineage, and access rules as structured, machine-readable context.
Agents evaluate dynamic business rules instead of relying on hardcoded branches or human interpretation.
Context layers are versioned, allowing policies to evolve over time and work cross-platform.
Instructions and policies are versioned, operational metadata. Plan/apply workflows like infrastructure-as-code.
Track every change with Git-style versioning and rollback capabilities.
Preview changes before deployment with impact analysis.
Pull request workflow for governance changes with team approval.
Preview changes
Team validation
Deploy to production
The rules governing data disappear the moment it crosses a system boundary. Keep those rules attached so every downstream system knows exactly what it received and how it can be used.
Restriction is a moving target. A boundary crossed, a threshold exceeded, a deadline passed. Structured context recognizes each condition and adapts.
Evaluate any data operation, rewriting what needs to change and preserving what’s permitted, before execution completes.
Capture the why behind every action, preserve full context, and create an audit trail for compliance.
Context that stays with your data ensures agents and systems make the same decisions across data workflows. No schema or semantic drift.
Context stored in separate systems
Passive documentation
Static schema and policies
Rigid implementations that break with updates
Structured, machine-readable context attached to data
Operational, decision-grade instructions
Adaptive decisions at runtime
Deploy once, version and evolve over time
Native warehouse integrations or cross-platform agent coordination. Adapts to how you work.
Deep native integrations means governance built into data development.
Multiple agents query the shared decision layer before accessing data. Structured context becomes the coordination protocol between agents.
Your decision layer is open at the MCP layer. Any agent that speaks the protocol reads it through the same Metatate tools. Claude Code does it first-class today.
Eight slash commands and a Claude skill that keep Claude grounded in your decision layer. Author policies, inspect rules, authorize use, validate queries — without leaving the editor.
Context that moves with your data. Agents and systems can coordinate, enforce policies, and validate compliance without manual oversight.
Agents combine data from multiple sources understanding calculations, relationships, and constraints without human translation.
Systems apply complex business logic consistently across workflows.
Governance happens automatically because agents understand constraints.