diff --git a/docs/content/docs/agent-sdk/benchmarks/index.mdx b/docs/content/docs/agent-sdk/benchmarks/index.mdx
index 59e9b7ad..6397b2ec 100644
--- a/docs/content/docs/agent-sdk/benchmarks/index.mdx
+++ b/docs/content/docs/agent-sdk/benchmarks/index.mdx
@@ -9,9 +9,9 @@ The benchmark system evaluates models on GUI grounding tasks, specifically agent
 
 ## Available Benchmarks
 
-- **[ScreenSpot-v2](./screenspot-v2)** - Standard resolution GUI grounding
-- **[ScreenSpot-Pro](./screenspot-pro)** - High-resolution GUI grounding  
-- **[Interactive Testing](./interactive)** - Real-time testing and visualization
+- **[ScreenSpot-v2](./benchmarks/screenspot-v2)** - Standard resolution GUI grounding
+- **[ScreenSpot-Pro](./benchmarks/screenspot-pro)** - High-resolution GUI grounding  
+- **[Interactive Testing](./benchmarks/interactive)** - Real-time testing and visualization
 
 ## Quick Start
 
diff --git a/docs/content/docs/agent-sdk/usage-tracking.mdx b/docs/content/docs/agent-sdk/usage-tracking.mdx
index 54bbcaae..2709d738 100644
--- a/docs/content/docs/agent-sdk/usage-tracking.mdx
+++ b/docs/content/docs/agent-sdk/usage-tracking.mdx
@@ -56,7 +56,7 @@ agent = ComputerAgent(
 )
 ```
 
-See also: [Budget Manager Callbacks](./callbacks#cost-saving)
+See also: [Budget Manager Callbacks](./callbacks/cost-saving)
 
 ## See Also
 - [Prompt Caching](./prompt-caching)