diff --git a/assets/image_1769673209665_0.png b/assets/image_1769673209665_0.png
new file mode 100644
index 00000000..dc86064a
Binary files /dev/null and b/assets/image_1769673209665_0.png differ
diff --git a/journals/2026_01_29.md b/journals/2026_01_29.md
index a6c3f5b5..d15cd86c 100644
--- a/journals/2026_01_29.md
+++ b/journals/2026_01_29.md
@@ -33,7 +33,9 @@ boox-notes:: ![BOOX Notes](../assets/../../onyx/TabUltraCPro/Notepad/JOURNALING.
 				- You said that the datasets are necessary to train the model. But it is sure that the existing models are nothing to do with agents or multi-agent systems. Isn't it? [[question]]
 			- ![image.png](../assets/image_1769673122545_0.png)
 				- I think you should focus on the workflow benchmarks [[question]]
-		-
+			- ![image.png](../assets/image_1769673209665_0.png)
+				- This should be looked also for our [[Benchmarking framework]]
+			-
 			- ### Questions
 				- {{query (and [[question]] [[29-01-2026]] )[[question]]}}
 				  query-table:: true
\ No newline at end of file