Overview

We aim to provide few but powerful core concepts to allow for flexible data ingestion, analysis and management. Foundation services like AI Models, a Geocoder or a Websearch tool can extend the functionality and allow for hybrid setups. From cloud to fully local on your own hardware.

Before you start: make sure everything is properly installed and configured.

Infospaces - your project spaces

Everything lives inside one - isolated from other projects, each its own vector index for semantic search.

Assets

Your content. Composable - a file decomposes into analysable units. Bundles group assets for organisation and analysis.

Schemas

Your lens and instructions for the AI. They are natural language tasks with strict definitions of the output.

Analysis

This is where it all comes together. With the building blocks above you are set to work through your data by configuring an analysis.

1. Configure an analysis run What questions do you want to answer? What data do you have? Also set up parametrs like parallelisation and if you want justifications for fields.