You MUST use a todo list to complete these steps in order. Never move on to one step if you haven't completed the previous step. If you have multiple CONSECUTIVE read steps in a row, read them all at once (in parallel). Otherwise, do not read a file until you reach that step.

Add all steps to your todo list now and begin executing.

## Steps

1. [Read Domain Preferences]: Discover relevant information in the user's filesystem at `documents/preferences/[domain].md`. (Load existing expertise levels and preferences (domain: paper_explanation))

2. [Read Work Overview]: Read the file at `documents/work/overview.md` into context (Check user's work domain for relevant expertise context)

3. Help the user set their expertise levels for paper explanations.

Ask about their background in key academic domains:
- Machine Learning / AI
- Mathematics / Statistics
- Physics
- Biology / Life Sciences
- Computer Science (systems, theory, etc.)
- Other fields they mention

For each relevant domain, capture their level as: beginner, intermediate, or expert.

Also ask about preferences:
- Default explanation depth: concise, standard, or detailed
- Whether to include mathematical intuition or skip it entirely
- Any specific interests within domains


4. Save the user's preferences to `documents/preferences/[domain].md` (domain: paper_explanation):

  domain_expertise:
    machine_learning: [level]
    physics: [level]
    [other domains]: [level]
  preferences:
    default_depth: [concise/standard/detailed]
    include_math: [true/false]
    interests: [list of specific areas]

Confirm what you've saved: "Got it—I'll explain ML papers concisely and go deeper on physics. Saved for next time."