Step 1
Upload
Drop in what you're trying to learn, exactly as it exists. No reformatting needed.
Supported: PDF, Markdown, DOCX, Notion export, Confluence export. GitHub and Google Drive coming soon.
THE PRODUCT
NotebookLM and Perplexity answer questions about your sources. SILKLEARN reads the structure through them.
Step 1
Drop in what you're trying to learn, exactly as it exists. No reformatting needed.
Supported: PDF, Markdown, DOCX, Notion export, Confluence export. GitHub and Google Drive coming soon.
Step 2
The dependency graph builds itself. Every node, every edge, inspectable before you follow it.
Inspect every connection. Accept it, reject it, or flag it for further review. The compiled structure doesn't become your path until you've verified it makes sense.
Step 3
Work through the path. Your documents, in the order they actually depend on each other.
Export as a structured reading list, share with a collaborator, or feed as structured context to an AI system that needs the right order, not a retrieval guess.
Dependency-ordered sequence through your sources from the first you add.
Every dependency visible and traceable back to its exact source section.
Every point where your sources disagree, surfaced before you build on them.
Structured, ordered context your agent can actually reason across.
Capabilities
01
PDF, MD, DOCX, Notion, Confluence. No reformatting.
02
Reads the order your documents already assume. Doesn't invent one.
03
Visual graph. Inspect every dependency connection. Accept, adjust, or flag before you start reading.
04
Timestamps and reviewer names logged as you review.
05
When two docs disagree, a conflict flag appears. You decide.
06
Every item traces back to the exact doc section it came from.
07
Notion · Confluence · Drive · GitHub · Slack · API (beta)
08
Docs change? Re-compile, review the delta, republish. Done.