diff --git a/docs/capability-parity.md b/docs/capability-parity.md
new file mode 100644
index 0000000..9161597
--- /dev/null
+++ b/docs/capability-parity.md
@@ -0,0 +1,52 @@
+# Capability parity — GSheet+GDrive → wanderbooks
+
+The parity target for the AI-first phase is **not QuickBooks**. It is the
+system actually in use today: the "Wanderland Labs LLC — Books" Google Sheet
+(double-entry accounts with live P&L, Balance Sheet, and Cash Flow tabs, plus
+the Transaction Journal) together with the Drive folder, operated through an
+AI assistant. Every capability below must be reachable through MCP tools
+before the sheet retires.
+
+Statuses: `covered` (the engine already does it), `specced` (designed in
+this phase, not yet built), `future` (on the engine roadmap).
+
+| # | Today's capability | wanderbooks equivalent | Status |
+|---|---|---|---|
+| 1 | Record a double-entry transaction (Transaction Journal row) | `books.draft_entry` / `add_line` / `post_entry` (engine: `Ledger`) | specced |
+| 2 | Chart of accounts | engine + `books.chart` (with live balances) | specced |
+| 3 | Live P&L tab | engine + `books.profit_and_loss` | specced |
+| 4 | Live Balance Sheet tab | engine + `books.balance_sheet` | specced |
+| 5 | Live Cash Flow tab | engine R-FUTURE-3 | future |
+| 6 | Transaction Journal as append-only log | engine posting log + `books.search_entries` | specced |
+| 7 | Receipt storage in Drive | blob store + `books.attach_receipt` / `link_receipt` | specced |
+| 8 | Document filing by category (01 Formation / 02 Legal / 03 Tax / 04 Accounting) | `books.file_document` | specced |
+| 9 | Ad-hoc questions ("what did we spend on X?") | `search_entries` + reports; the AI itself is the query layer | specced |
+| 10 | Human review of what the assistant recorded | `books.digest` | specced |
+| 11 | CPA-ready export of the books | `books.export` (csv/json) | specced |
+| 12 | Company email filing (every company email → Drive folder) | out of books scope; the existing mail-filing automation keeps running unchanged | — |
+
+## Notes
+
+- Row 9 is the quiet superpower of the AI-first design. The sheet answers
+  questions with formulas the human must write; the MCP design answers them
+  with an agent that already knows how to read a trial balance. The
+  capability is "ask anything about the books," and the tool surface above
+  is what makes it true.
+- Row 10 (`books.digest`) has no sheet equivalent — the sheet can't tell you
+  what changed. This is parity *plus*: the new system is more reviewable
+  than the old one, which is the point of the exercise.
+- Row 12 is deliberately excluded. Email filing is a mail problem, not a
+  books problem; it stays where it is.
+
+## Cutover rule
+
+The sheet does not retire on a date. It retires when **all three** hold:
+
+1. Every `specced` row above is `covered` (built, tested, golden-covered
+   where reports are involved).
+2. A full month of parallel run — every real company transaction recorded in
+   both systems — diffs clean.
+3. Stephen says so.
+
+The parallel run is the acceptance test. Until then the sheet is the system
+of record and wanderbooks is the shadow ledger; after, it inverts.