Add image.

apps/www/_customers/mendableai.mdx

@@ -48,6 +48,8 @@ Mendable lear that Supabase supports [pgvector](https://supabase.com/docs/guides
 
 Using [Supabase Vector](https://supabase.com/vector), Mendable was able to build a more efficient and accurate search function for their AI chatbot. By storing vector data alongside metadata in Supabase, Mendable was able to quickly and easily search through their customers documentation to find the most relevant responses to queries. They found that Supabase's solution was just as performant as dedicated vector databases, but without the high cost.
 
+![Mendable -build AI chat search applications](/images/customers/mendable/mendable.png)
+
 ## The Results
 
 Thanks to Supabase Vector, Mendable was able to significantly improve the efficiency and accuracy of their Chat Powered Search for Documentation. They were able to build faster and more cost-effectively using Supabase’s open source stack.