What is Flume

ContextBase understands your data and keeps what it means. It connects to the systems where your data lives: databases, warehouses, code repositories, documentation wikis, BI tools, and ETL platforms. From how data moves through the whole estate, it builds a knowledge graph of what that data means. Not just “this table has 12 columns,” but “this column is the claim line’s allowed amount after the lesser-of rule, set by a stored procedure, documented in the benefits configuration wiki, and read by the monthly paid claims dashboard.”

In ContextBase you browse your data, ask questions in Chat, see which payer value cases your data supports in Value Lab, and build dashboards, apps, and bots. Every answer arrives with its receipts and its answer checks.

Data Pipelines moves regulated payer data in production, and it is where Flume started. It moves and transforms data between systems: any protocol, any schedule, any combination. Source endpoints, destination endpoints, and a canonical data lake in the middle, each with its own mapping and transform logic.

The two products work together. When you need a new pipeline, ContextBase already knows your data estate: where the data lives, how it is structured, what the join keys are, and what validation rules apply. Drop in a new vendor spec and ContextBase can work out the map: where to pull data from, how to join it, how to validate it, and how to keep that pipeline running.

The more pipelines you run, the more context you generate, and the more context you have, the faster the next piece of work goes.

Who they are for

ContextBase and Data Pipelines are used by data engineers, integration teams, and business analysts who need to understand and operate within complex data estates. You can work with them four ways.

Application

Visual interface: Data, Chat, Value Lab, Dashboards, Apps, and Bots.

CLI

Command line interface. Supports both structured workflows and natural language queries.

MCP server

For LLM integration.

API

For programmatic access.