Skip to content

In-App Chat

The Chat panel lets you review sources inside FeynmanLM instead of opening Claude, ChatGPT, Gemini, or Grok. It uses the API provider and model you configure in Settings, so you can keep the whole learning loop in one app while still controlling which AI service processes your data.

What Chat does

Use in-app Chat when you want to:

  • Ask questions about selected sources
  • Run a source-grounded Feynman review
  • Start today's Schedule work without switching apps
  • Save the review session back into FeynmanLM automatically
  • Keep a transcript that future sessions and Studio can inspect

Chat is source-grounded. Add sources to the current context or open a scheduled source, then start a review from the Chat panel.

Feynman reviews

FeynmanLM's review flow asks you to explain ideas in your own words. The tutor probes gaps, asks follow-up questions, and records the exchange as a Feynman session.

Completed in-app reviews are linked to the source IDs they covered. That link is what updates Reviewed status in Studio and allows Schedule items to be marked done.

Review history

The Chat panel includes a review-history sidebar. It shows in-app reviews as well as external Claude, ChatGPT, Gemini, or Grok review links saved into FeynmanLM.

Stored sessions can include:

  • The source IDs reviewed
  • The transcript or recorded exchanges
  • The completion status
  • The score and summary when available
  • Start and end timestamps

Voice input

The Chat panel supports voice dictation for review answers. Audio is recorded temporarily and sent to your configured speech-to-text provider, or processed on-device when you choose an on-device option. Raw voice audio is not persisted.

API keys and errors

In-app Chat uses the provider and model configured in Settings. Provider usage charges can apply. If the selected provider or model cannot complete the request, FeynmanLM should surface the error instead of silently switching to heuristic grading or fallback feedback.

External AI assistants are still supported. Drag and drop remains the quickest no-setup workflow, and MCP remains the best option when you want Claude, ChatGPT, Gemini, or Grok to search and manage the full library.