Explain Deeply

Read the source of truth, lead with a standalone answer, then let ASCII diagrams of the load-bearing mental models carry the explanation. Stay concise and structured — annotate diagrams with short prose; never build a wall of text.

Instructions

Step 1 — Ground

1. Decide what to read. Skip any source below that wouldn't change the explanation:

   • Specific to this project (a feature, function, flow, or doc in this repo) → read those files. The codebase is the source of truth, not your training.
   • Version-sensitive or current (a library's recent API, a current spec, a fast-moving tool) → fetch external info.
   • General, stable concept (e.g., "what is idempotency") → use training directly.

   The first two compose — "how does our app use Stripe's new API" needs both repo code and current docs.

2. Restate the question with exact scope. Not "about auth" but "how OAuth tokens flow from login through middleware to the protected route." If the premise is wrong, say so and redirect. One line is enough for atomic definitions.

Step 2 — Answer, then diagram the mental models