diff --git a/README.md b/README.md
index a2d023b..66f0b5f 100644
--- a/README.md
+++ b/README.md
@@ -12,9 +12,9 @@ Are you frustrated with vector database retrieval accuracy for long professional
**[PageIndex](https://vectify.ai/pageindex)** is a *document indexing system* that builds *search tree structures* from long documents, making them ready for reasoning-based RAG.
-You can self-host it with this open-source repo, or try our ☁️ [Cloud service](https://pageindex.vectify.ai/) — no setup required, with advanced features like OCR for complex PDFs.
+Self-host it with this open-source repo, or try our ☁️ [Cloud service](https://pageindex.vectify.ai/) — no setup required, with advanced features like OCR for complex and scanned PDFs.
-PageIndex powered a reasoning-based RAG system that achieved a 98.7% accuracy on [FinanceBench](https://vectify.ai/blog/Mafin2.5), demonstrating state-of-the-art performance on financial document retrieval.
+PageIndex powers a reasoning-based RAG system that achieved a 98.7% accuracy on [FinanceBench](https://vectify.ai/blog/Mafin2.5), demonstrating state-of-the-art performance on financial document analysis.
Built by Vectify AI