Language models answer fluently. To act on an answer about your data, you need to see what it rests on.
Summand and Elbi put a layer of components between your data and the AI. A component is a result you can read, like a table of feature effects or the distribution of one column. The AI answers from those components, so its answers have something underneath them you can check.
Data
CSV uploads and database connectors
Components
Computed, versioned, readable
AI systems
Summand chat, or any MCP client
Something found or fitted about your data, written down so a person or an agent can read it. Summand has eleven you can pick, five of them in beta. In Elbi a component comes from a derivation, a Python function you can open and change.
Connect your data
Upload a CSV, or on Enterprise connect Postgres, Snowflake or another database. Summand copies your data into its own Iceberg store; Elbi pulls from your sources on your machine.
Compute components
Tools compute what's true about the data: distributions, feature effects, correlations, fitted models. They run when a person or agent asks, and on any schedule you set.
Keep every result
Each component is stored with the dataset it came from and the time it was computed. A re-run adds a new version and leaves the old one where it was.
Answer from the results
When a model needs to know something about your data, it calls a tool and gets back a small structured result it can read and cite. Summand's chat works this way, and any MCP client can call the same tools.
Reuse them
The next question, app or agent starts from the stored component.
A semantic layer holds the rules people wrote down. The empirical layer holds what the data actually does: every finding, with the data and run behind it. More on the empirical layer →
Answers trace back to components you can open: an EBM's feature effects, a column's statistics, the data and model that produced them. That's what makes AI deployable where transparency is required.
Two teams read the same table two ways, and an AI system invents a third. Compute the answer once as a component, and people and agents all read the same thing.
Components persist and re-run on a schedule you set, so each analysis starts from the last one.
Components reach any AI system over MCP and stay put when you switch providers. Summand's built-in assistant runs on Claude; Elbi works with whatever model your client brings.