diff --git a/docs/docs/snippets/prompt-syntax/output-format.mdx b/docs/docs/snippets/prompt-syntax/output-format.mdx
index 78580269e..414f29657 100644
--- a/docs/docs/snippets/prompt-syntax/output-format.mdx
+++ b/docs/docs/snippets/prompt-syntax/output-format.mdx
@@ -35,6 +35,7 @@ Bachelors CS, 2015
 UT Austin
 ---
 
+Answer in JSON using this schema: 
 {
   name: string
   education: [
@@ -128,4 +129,4 @@ The tl;dr is that json schemas are
 2. very unreadable by humans (and hence models)
 3. perform worse than type definitions (especially on deeper nested objects or smaller models)
 
-Read our [full article on json schema vs type definitions](https://www.boundaryml.com/blog/type-definition-prompting-baml)
\ No newline at end of file
+Read our [full article on json schema vs type definitions](https://www.boundaryml.com/blog/type-definition-prompting-baml)