Uploading research

Everything you upload to Crux is parsed and indexed so AI skills and search can use it as evidence.

Supported sources

• Documents — PDF, Word (.docx), PowerPoint, plain text and markdown.
• Spreadsheets — Excel (.xlsx), CSV.
• Transcripts — interview/meeting transcripts as text or documents; audio transcript formats are supported for imported transcriptions.
• Web links — website nodes unfurl and capture page content.
• Google Drive (paid plans) — see Google Drive & Figma.
• Figma (coming soon) — design-frame import is on the roadmap; see the same article for updates.

What happens on upload

1. Parsing — Crux extracts the text (including PDF text layers and Office document content).
2. Chunking — long documents are split into overlapping chunks.
3. Embedding — each chunk gets a vector embedding so semantic search and skills can retrieve exactly the relevant passages.
4. Preview — a preview is generated for quick reading inside the app.

Indexing runs in the background; very large files may take a minute before they're fully searchable.

Files on the canvas

Uploads live in the Uploads panel and can also be placed as file nodes on the canvas. Connecting a file node to your analysis nodes tells skills to treat that file as upstream context.

Tips for better AI output

• Prefer text-first files. Scanned image-only PDFs have no text layer to extract.
• Split monster documents. Several focused files retrieve better than one 300-page compendium.
• Name files meaningfully. File names appear in search results and citations.

Storage

Each plan includes a storage allowance (from 200 MB on Free up to 50 GB on large team plans by default). Deleting a project removes its files, previews, and embeddings.