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

​
How Artifacts Work

1

Thread Creation

Each agent execution gets a unique thread ID and isolated storage
2

Input Files

Uploaded files are placed in the thread’s input directory
3

Processing

Agent reads input files and generates output files
4

Output Files

Results are written to the thread’s output directory
5

Retrieval

Download output files via UI, CLI, or API

​
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:
  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.
⌘I