Studio

The Studio tab is where all your sources live. It's the central place to add content, read or listen to it, schedule it for review, and chat with an AI tutor.

Layout

Studio has four main panels, all resizable and toggleable:

Panel	What it does
Sources (left)	Your source queue, organized by type tabs
Reader	Displays the selected source: web article, PDF, video, or transcript
Chat	In-app source-grounded chat and Feynman review sessions
Schedule (right)	Weekly learning plan, daily assignments, and progress

How sources get in

Sources flow into Studio from multiple directions:

• Browser reading lists — Safari, Chrome, and Brave reading lists are scanned automatically
• Apple Podcasts — episodes you've listened to appear after you view the transcript once in Podcasts.app
• Local files — PDFs placed in the Books, Courses, or Papers folders in iCloud are discovered automatically
• Manual paste — paste any URL into the source bar
• AI assistants — Your AI assistant can add sources via the MCP connection
• X (Twitter) — sign in to sync your bookmarked posts

Each source type has its own tab in the sidebar. See the dedicated guides for details on Articles, Papers, Books, Courses, Podcasts, and X Posts.

Source lifecycle

Every source moves through a simple flow:

1. Queued — source discovered, content not yet fetched
2. Ready — content loaded and stored in the database, available for reading and MCP access

Once a source is ready, its full text is accessible to any connected AI assistant via the get_source_content or get_app_context MCP tools.

Ready is an import state, not a learning-completion state. Studio does not mark sources read or unread.

Schedule

Use Schedule to assign sources to specific days and track the week's learning progress. You can drag sources or groups onto a day, move scheduled items between days, remove sources, or clear a day when plans change.

Schedule completion is tied to reviewed status. A source should be marked done only after a completed or linked Feynman review covers it.

Reviewed sources

A source becomes Reviewed only after you go back to it with an AI tutor and complete a Feynman-style review session that covers the main points.

Reviewed status comes from linked sessions:

• completed Feynman sessions started through MCP
• completed Feynman sessions from the in-app Chat panel
• saved Claude, ChatGPT, Gemini, or Grok session links attached to the source

Studio shows the reviewed date in the source row. That date is used as the anchor for future spaced-repetition scheduling.

In-app Chat

The Chat panel lets you ask questions and run reviews without leaving FeynmanLM. It uses the API provider and model configured in Settings, records review exchanges, and links completed sessions back to the sources they covered.

The review-history sidebar includes both in-app sessions and external chat links saved from Claude, ChatGPT, Gemini, or Grok.

Read Aloud

Use Read Aloud from the Reader toolbar or source menu to listen to articles and text sources. The playback bar supports pause/resume, 15-second seeking, speed controls, and stop.

Text-to-speech settings live in Settings -> Text-to-Speech. On-device macOS speech is available for local playback, and cloud TTS providers can generate cached audio when configured with API keys.

Using sources with AI assistants

Add sources to the context tray at the bottom of the sidebar, then drag them into Claude, ChatGPT, Gemini, or Grok. Your AI assistant can then:

• Answer questions about the content
• Compare ideas across multiple sources
• Quiz you on the material using the Feynman technique
• Probe your understanding with Socratic dialogue

For hands-free access where your AI can search your entire library without dragging, you can optionally set up the MCP server via Tailscale.

Semantic search

Use semantic search to find sources by concept across your entire library. This uses vector embeddings to find semantically similar content, not just keyword matches.

Your AI assistant can also search your sources programmatically via the search_sources_semantic MCP tool.

LLM calls during import

FeynmanLM uses lightweight LLM calls at two points during source import. These require API keys configured in Settings → API Keys.

What	Model	When	Why
Source classification	Claude Haiku (Anthropic API key)	When a URL matches a journal domain (Nature, Science, etc.)	Journals publish both research papers and editorial content on the same domain. The LLM distinguishes papers from news/commentary so they land in the right tab. Also runs after fetching article content to catch papers hosted on non-academic domains.
Transcript cleanup	GPT-4o-mini (OpenAI API key)	After extracting a YouTube or podcast transcript	Raw auto-generated transcripts lack formatting. The LLM adds paragraph breaks, speaker labels, and removes filler words while preserving all substantive content.

Both calls are optional — if the relevant API key is missing, the feature is skipped gracefully (sources still import, transcripts are just unformatted).

Dealing with paywalled content

When Studio can't fetch content (HTTP 403), it checks for a local PDF:

• Papers: save the PDF to iCloud Drive → Documents → FeynmanLM → Papers
• Articles: save the PDF to iCloud Drive → Documents → articles

The app uses fuzzy filename matching, so exact names aren't required. You can also drag and drop a PDF directly onto the source in Studio.

For papers specifically, open-access sources (arxiv, bioRxiv, PLOS, PMC) are fetched automatically. See the Papers guide for details.

Tips

• Add sources to the context tray before dragging. Only sources in the tray are included when you drag into a chat.
• Use semantic search to find connections between sources you might not have noticed.
• Batch processing: sources stay in your queue until you're ready. No rush to process everything immediately.