> ## Documentation Index
> Fetch the complete documentation index at: https://docs.palliora.org/llms.txt
> Use this file to discover all available pages before exploring further.

# Concepts

Palliora AI builds directly on Palliora's core concepts, not a separate protocol. Start with [Core concepts](https://docs.palliora.org/ai/learn/concepts/core-concepts.md) if you're new, then come back for what's specific to Palliora AI below.

> [card] [Core concepts](https://docs.palliora.org/ai/learn/concepts/core-concepts.md)
>
> A short map of which Palliora core concepts matter most for Palliora AI, and why, with links to the full pages.

> [card] [Tool calls and agent runs](https://docs.palliora.org/ai/learn/concepts/tool-calls-and-agent-runs.md)
>
> How a multi-step agent run breaks down into one Compute Contract per model or tool call.

> [card] [Provenance](https://docs.palliora.org/ai/learn/concepts/provenance.md)
>
> The record a Palliora AI run leaves behind: which models and tools ran, and the agreements that coordinated them.


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.