Glossary
The language of governed AI analytics.
Clear definitions of the terms behind Nexatron — the semantic layer, MetricQL, MCP, calibrated answers, and the governance that makes every answer trustworthy for both people and the agents they trust.
- Semantic layer
- A semantic layer is a governed model that maps raw database tables and columns to the business concepts people reason in — metrics, dimensions, and the relationships between them — so a question can be answered the same way every time, regardless of who asks. In Nexatron the semantic layer is expressed in MetricQL and underpins certified metrics, so a query resolves to one agreed definition rather than ad-hoc SQL.
- MetricQL
- MetricQL is the declarative language Nexatron uses to define metrics, dimensions, hierarchies, and joins as reusable building blocks in the semantic layer. Because every metric is defined once in MetricQL and compiled to warehouse SQL at query time, the same definition powers natural-language questions, certified-metric lookups, and agent queries — giving consistent numbers across every surface.
- Model Context Protocol (MCP)
- The Model Context Protocol (MCP) is an open standard that lets AI agents and applications connect to external tools and data through a consistent, structured interface instead of bespoke integrations. Nexatron exposes an MCP server over Streamable HTTP (JSON-RPC 2.0) secured with OAuth 2.1, so an MCP-capable agent such as Claude, ChatGPT, or Cursor can ask governed questions, discover and run certified metrics, and trigger actions under the same governance as a human user.
- Calibrated answer
- A calibrated answer is a response that ships with the evidence needed to trust it rather than a bare number you have to take on faith. Every Nexatron answer returns the result rows, the exact query that produced them, the data lineage, and a confidence score — so a person or an agent can judge how much to rely on it before acting.
- Confidence score
- A confidence score is a quantitative signal of how much weight to put on a generated answer, exposed so the reader can calibrate trust instead of guessing. Nexatron returns a confidence score with every answer, alongside the generated SQL and lineage, so low-certainty results are visible and can be reviewed before they drive a decision.
- Governed analytics
- Governed analytics is the practice of putting analytics behind enforced controls — who can see what, how each metric is defined, and a record of every query — so results are consistent, permissioned, and auditable. Nexatron applies four-layer row-level security, certified metrics, and a hash-chained audit log to every query, and applies the same governance whether the request comes from a person or an AI agent.
- Natural-language-to-SQL (NL→SQL)
- Natural-language-to-SQL (NL→SQL) is the translation of a plain-language question into an executable SQL query so non-technical users can query a database directly. In Nexatron the model's output is treated as untrusted and validated against the semantic layer before any query runs, and the generated SQL is returned with the answer so the translation is always inspectable.
- Certified metric
- A certified metric is a business measure — like revenue or active users — whose calculation has been reviewed and approved as the canonical definition, so different teams don't compute it different ways. Nexatron stores certified metrics in the semantic layer and lets people and MCP-capable agents discover and execute them, ensuring the answer to "what's revenue?" is the agreed one every time.
- Row-level security
- Row-level security (RLS) restricts query results so each user sees only the rows they are permitted to — for example, a regional manager seeing only their region's records. Nexatron enforces four-layer row-level security at query execution, and applies it identically to human and AI-agent queries so an agent can never read rows its user could not.
- Cross-source federation
- Cross-source federation is the ability to run a single query that combines data living in different systems without first copying it all into one place. Nexatron federates across its nine supported warehouse, database, and file connectors using an embedded DuckDB engine, so a question can join data from more than one source while governance still applies.
- Self-healing semantic layer
- A self-healing semantic layer is one that detects when underlying schemas change — renamed columns, new tables, shifted types — and adapts its model so questions keep resolving instead of failing silently. Nexatron's semantic layer surfaces and reconciles this drift, reducing the manual upkeep that normally keeps a metric model accurate.
- Lineage
- Data lineage is the documented trail of where a result originated and every transformation applied to produce it, so a number can be traced back to its sources. Nexatron returns lineage with every answer — alongside the exact query and a confidence score — so anyone reviewing a result can see precisely which sources and logic produced it.
See these ideas at work
Connect a warehouse, ask in plain English or over MCP, and get a calibrated answer with the exact query, lineage, and a confidence score behind it.