The LLM never executes tools directly.
It produces a structured plan (Intermediate Representation). The orchestrator validates and executes — so a hallucinated function call cannot reach your database or your network.
datarelix.ai is built so that "we sent your data to an LLM" is never a true statement.
It produces a structured plan (Intermediate Representation). The orchestrator validates and executes — so a hallucinated function call cannot reach your database or your network.
We use sqlglot to parse every generated query into an AST. Statements outside an allow-list (read-only SELECT) are rejected. Automatic LIMIT enforcement.
Analysis runs in an isolated runtime with strict CPU and memory caps and zero network egress. The sandbox cannot exfiltrate data even if compromised.
Connections are encrypted at rest. The LLM sees schema metadata only. The MCP tier holds credentials and runs queries on the orchestrator’s behalf.
Every run is a step-by-step trace: who asked, what plan the LLM produced, what the orchestrator actually executed, what came back. Exportable.
Question
Sent to the LLM along with schema metadata only — never your data.
Plan
Structured IR returned by the LLM. Validated against the IR contract.
Execution
Orchestrator dispatches each step to MCP (for SQL/KQL) or Sandbox (for Python).
Result
Artifacts (tables, charts) returned to the user. Stored alongside the run trace.
Sign in with Google Workspace, Microsoft Entra (Azure AD), or GitHub. For Azure SQL/Synapse, Databricks, and Kusto, we support per-user On-Behalf-Of so a connection inherits the signed-in user’s database permissions instead of running as a shared service principal.
datarelix.ai is a fully managed service operated by datarelix.ai. Reach out via the contact page for our security questionnaire, SOC 2 status, and DPA.