Skip to main content

​
Overview

The Corvic Platform is built around several core concepts that work together to transform your enterprise data into actionable insights. Understanding these concepts will help you make the most of the platform.

​
Organization

An Organization in the Corvic Platform refers to the overall structure that manages users, roles, and data rooms. Each organization’s data is isolated from others and receives dedicated workload execution. As an admin, you have full access to all data rooms and their functionalities within your organization.

​
Data Room

A Data Room is an exclusive workspace where you can upload and manage your ingestion pipelines, generate Corvic Tables, run spaces, and create agents. Each data room is isolated, meaning the data, Corvic Tables, spaces, and agents in one room are not accessible from another.

Learn more about Rooms

Detailed guide on creating and managing data rooms.

​
Ingestion Pipeline

An Ingestion Pipeline collects and transforms raw data that you upload to a data room for further processing. This raw data can be in the form of text documents, tables, or databases. It’s important to ensure the data is clean and well-structured to maximize the effectiveness of the platform’s transformation and embedding tools.

​
Corvic Table

A Corvic Table is a distributed processing construct that defines what entity, object, or operational unit you want to work with across your data. Rather than being tied to a single data source or format, a Corvic Table composes multiple contributing inputs—structured, unstructured, or multimodal—into a unified, addressable representation. Corvic Tables serve as the backbone for distributed data processing and transformation. They let you declaratively specify how complex data should be joined, enriched, normalized, and evolved at scale—without hard-coding brittle pipelines. Each table becomes a logical unit for computation, enabling scalable transformations, feature generation, operational analytics, and downstream AI workflows. By abstracting what the entity is from how the data is physically stored or processed, Corvic Tables allow teams to build reusable, composable intelligence that runs efficiently across distributed data infrastructure.

​
Example

Suppose you have uploaded two parquet files:
  • accounts.parquet (Account) - list of financial accounts
  • transactions.parquet (Transaction) - list of financial transactions between pairs of accounts
You can create a Corvic Table to represent your account IDs by using both Account and Transaction as input sources and introducing Account.account_id as the space key.
A Corvic Table specifies what needs to be converted to embeddings, but it doesn’t explain how it should be embedded.

Learn more about Corvic Tables

Detailed guide on creating and configuring Corvic Tables for distributed processing.

​
Space

A Space refers to the process of transforming your defined Corvic Tables into embeddings. Here, you specify the “how” - the method of embedding. This involves selecting an algorithm, setting parameters, and initiating the space. Once the space is complete, your embeddings are ready for analysis and export.
A Space details how to use input sources in your Corvic Table to generate embeddings for each key defined by the output entities within that Table.

Learn more about Spaces

Detailed guide on creating and analyzing spaces.

​
Agent

An Agent refers to a natural language processing entity that utilizes an LLM-powered orchestration mechanism to execute multi-space traversal workflows tailored to user’s inquiries. Each agent is configured with a set of input spaces (along with specific instructions for using those spaces) and parameters for the completion LLM.
An Agent plans how to leverage multiple embedding spaces to derive enterprise insights for user queries.
The agent combines information from multiple embedding spaces to generate enterprise insights, leveraging the LLM for enhanced reasoning. This process involves orchestrating pre-configured spaces and the LLM to execute policies that address complex queries across various data spaces.

Learn more about Agents

Detailed guide on creating and configuring agents.

​
Data Flow (Data Apps & Intelligence Operations)

Here’s how these concepts work together in Corvic: Ingest Data → Connect and sync data from files, object stores, databases, and live systems into Data Rooms. Compose Entities & Logic → Define Corvic Tables to model domain entities, operational units, and business logic across multiple data sources. Transform & Enrich → Apply distributed processing to clean, join, enrich, and structure complex data—powering analytics, features, and domain intelligence. Build Data Apps & Intelligence → Assemble agents, analytics, and workflows on top of Corvic Tables to explore data, automate reasoning, and drive operational decisions.

Architecture Overview

Learn more about the Corvic Platform architecture.