AI Co-Builder: Arc (or just Arc) is a coding agent built directly in CX Agent Studio. It is equipped with all of the skills necessary to build agent applications:
- Multi-agent architectures
- Instructions
- Tool implementations (for instance: OpenAPI tools and Python tools)
- Callback implementations
- Guardrails
- Versions
To use Arc, click the Arc icon at the top of the agent builder, then provide your prompt to the agent.
Uploading files
You can attach files to a message to give Arc more context: a product requirements document, a sample data file, details of external services that need to be called, or an archive of existing configuration.
Arc handles files in three ways, depending on the format:
| How it is used | Formats | What happens |
|---|---|---|
| Read directly | PDF, PNG, JPG, JPEG, WAV, OGG | The file is provided to the model as-is. |
| Read as text | TXT, MD, JSON, CSV, HTML, JS, XML, RTF, CSS | The file's text is added to your message. Only the first 262,144 characters are included; ask Arc to read further if the file is longer. |
| Unpacked | ZIP | The archive is extracted and its text files become searchable. The archive itself is not sent to the model, and non-text entries inside it are listed but not read. To let Arc read a non-text file that is inside a ZIP archive (a PDF or an image, for example) upload that file directly instead. |
The following file limitations apply:
- Up to 5 files per message
- Maximum file size of 20 MB
- Maximum ZIP archive size of 500 MB
Uploads go to a Cloud Storage bucket in your own project,
named PROJECT_ID-agent-assist-artifacts,
under the agent-assist-uploads/ prefix.
If the bucket does not exist,
the console creates it the first time you upload a file,
which requires the storage.buckets.create permission.
Uploading requires storage.objects.create.
Uploaded files are deleted automatically 75 days after upload, under a lifecycle rule applied when the console creates the bucket. If the bucket already existed, its own lifecycle policy applies instead.
Chain of thought
While processing, Arc provides its chain of thought in sections. You can expand any of these sections to get detail on the agent reasoning.
Select context
Within the prompt dialog, you can click the Select context button, then add select items that Arc should use for additional context in your prompt. For example, you can click this button, followed by a particular agent in the agent builder, then ask Arc to explain the agent to you.