Uploading Documents

Every project in ADD CREATE is powered by a knowledge base — the documents you upload. These are what the AI draws from when generating audio overviews, videos, and infographics. The AI works exclusively from your files, so the quality and completeness of what you upload directly shapes what gets generated.

Supported File Types

You can upload files in the following formats:

Format	Extension
PDF	.pdf
Word Document	.docx
PowerPoint	.pptx
Plain Text	.txt
Markdown	.md
HTML	.html, .htm
CSV	.csv

System and temporary files — such as hidden Mac metadata files or Office auto-save files — are automatically ignored during upload.

How to Upload

1. Open your project and go to the Files tab.
2. Click Upload Files or drag and drop files into the upload area.
3. You can upload individual files or entire folder structures — the platform preserves your folder hierarchy.
4. After uploading, processing begins automatically.

What Happens After You Upload

Once files are uploaded, the platform reads each document, breaks it into sections, and makes those sections searchable. This background process is what allows the AI to find and use the most relevant parts of your documents when generating content — rather than processing the entire thing every time.

Processing Status

You can track progress on the project page or Files tab:

Status	What it means
Pending	No files have been processed yet
Running	Processing is currently in progress
Ready	All files are indexed and the Studio is unlocked
Failed	Something went wrong — check the Files tab for details

Important

The Studio is locked until your project status reaches Ready. If processing fails, you can re-upload the affected file or contact your administrator.

Managing Your Files

From the Files tab you can:

• View all uploaded files along with their name, size, and upload date.
• Re-process a file if its content has changed since the original upload. The file row shows Reprocessing and disables the reprocess action while the update is running.
• Delete a file, which removes it from the project knowledge base. Content generated before the deletion is not affected.

Duplicate Files

If you upload a file that is identical to one already in the project, the platform detects this automatically and skips re-processing it. This prevents duplicate content from affecting the knowledge base.

Advanced Usage Notes

Use these patterns to get more predictable results:

• Keep inputs specific and scoped to one intent per generation request.
• Save intermediate outputs often, especially before running major edits or regenerations.
• Use review and assignment workflows early to reduce rework late in the lifecycle.

Troubleshooting

If results are not what you expected:

• Verify source quality first (missing context, inconsistent structure, or conflicting inputs reduce output quality).
• Re-check selected options and audience/profile settings before re-running.
• If a job fails repeatedly, wait briefly and retry once; then escalate with the artifact or job context.

Frequently Asked Questions

Why did quality change between runs?

Different input context, settings, and model/runtime conditions can produce different outputs.

Should I regenerate or manually edit?

Regenerate when the core structure is wrong; manually edit when only wording, ordering, or style needs adjustment.

What is the best way to reduce iteration cycles?

Start with clear scope, run smaller batches, and use review checkpoints after each major step.