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

# Artifacts

> Understanding the artifacts system

The artifacts system uses separate file storage for each agent execution. Each thread has its own input and output directories.

<Info>
  Files are thread-scoped by design; cross-thread access is blocked by platform policy but should not be relied on as a hard security boundary.
</Info>

## How Artifacts Work

<Steps>
  <Step title="Thread Creation">
    Each agent execution gets a unique thread ID and isolated storage
  </Step>

  <Step title="Input Files">
    Uploaded files are placed in the thread's input directory
  </Step>

  <Step title="Processing">
    Agent reads input files and generates output files
  </Step>

  <Step title="Output Files">
    Results are written to the thread's output directory
  </Step>

  <Step title="Retrieval">
    Download output files via UI, CLI, or API
  </Step>
</Steps>

## File Structure

Each thread has this directory layout:

```
artifacts/
└── threads/
    └── abc123-def456/           # Thread ID
        ├── input/                # Input files
        │   ├── data.csv
        │   └── config.json
        └── output/               # Output files
            ├── results.csv
            └── report.pdf
```

## Uploading Input Files

### Via UI

In the agent detail page at [http://localhost:3001](http://localhost:3001):

1. Click **Choose Files**
2. Select files to upload
3. Files appear in the input list

## Downloading Output Files

### Via UI

Navigate to the execution details to see output files. Click to download.