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

# Companion documents

> The document family the working paper anchors: manifesto, technical papers, platform architecture, and the standards that follow.

The paper anchors five companion documents, each with a different job:

| Document                                                      | Purpose                                                                                                       | Status  |
| ------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------- | ------- |
| The Agent Applications Manifesto                              | A short public argument for software that does the work                                                       | Planned |
| Programming Agent Applications                                | The programming model, harness interpreter, packaging, runtime feature declarations, and evaluation           | Planned |
| Persistent Agent Instances: Workspace, Artifacts, and Lineage | Agent projects, instances, durable workspaces, state, overlays, upgrades, and recovery                        | Planned |
| The Agent Application Platform: A Platform Architecture       | Production infrastructure and commercial services derived from the application contract                       | Planned |
| Agent Artifact Standard                                       | A portable contract for artifact content, identity, provenance, permissions, versions, rendering, and actions | Planned |

## From contracts to standards

The paper identifies several possible open contracts. A contract is ready for
standards work when two or more independent implementations need the same
stable boundary. The likely order is:

1. **Agent Application conformance and package contract.** This would define
   the minimum portable declaration of programs, capabilities, permissions,
   evaluations, and workspace requirements.
2. **Agent Artifact contract.** This would cover identity, content and state,
   provenance, permissions, versions, rendering, and actions. See
   [Agent Artifact](/concepts/artifact) for the two-layer model.
3. **Workspace and lineage export.** This would carry portable state and its
   release and overlay history, using secret references instead of credentials.
4. **Agent identity and delegated authority.** This work comes later, after
   principal and cross-system authority models are mature enough to support a
   shared abstraction.

When the first contract is ready, it will appear here as a versioned
specification with its own change process, following the model established by
the Model Context Protocol.