diff --git a/README.md b/README.md
index e69de29..f96621d 100644
--- a/README.md
+++ b/README.md
@@ -0,0 +1,17 @@
+**Comprehensive, LLM-Testable Specification for the “AI Bulk Image Renamer” SaaS**
+
+### 0. Terminology
+01. *Batch* = one drag-and-drop upload event containing ≤ N images, where N depends on the user’s plan.  
+02. *Basic* = default free plan, quota = 50 images / calendar month.  
+03. *Pro*   = paid plan,   quota = 500 images / calendar month.  
+04. *Max*   = paid plan,   quota = 1 000 images / calendar month.  
+05. *Keyword Set*          = the list of keywords a user provides or the system extends.  
+06. *Enhanced Keyword Set* = Keyword Set after pressing “Enhance keywords with AI”.  
+07. *AI Vision Descriptor* = tags the vision model returns for one image.  
+08. *Proposed Filename*    = final, human‑readable name generated for one image.  
+09. *Review Table*         = screen listing every original filename beside its Proposed Filename before download.  
+
+### 1. High‑Level Goals
+10. The product shall let any authenticated user rename many images in one batch using a combination of user‑supplied keywords and automatic computer‑vision tags.  
+11. The product shall output renamed images that are search‑engine‑friendly, syntactically safe for all major file systems, and semantically descriptive of image content.  
+12. The product shall monetise via tiered monthly quotas and Stripe‑handled subscriptions.