diff --git a/docs/getstarted/evals.md b/docs/getstarted/evals.md
index 249f03928..a04851dd0 100644
--- a/docs/getstarted/evals.md
+++ b/docs/getstarted/evals.md
@@ -62,7 +62,7 @@ choose_evaluator_llm.md
 **Evaluation**
 
 
-Here we will use [AspectCritic](../concepts/metrics/available_metrics/aspect_critic.md), which an LLM based metric that outputs pass/fail given the evaluation criteria.
+Here we will use [AspectCritic](../concepts/metrics/available_metrics/aspect_critic.md), which is an LLM based metric that outputs pass/fail given the evaluation criteria.
 
 
 ```python
@@ -148,8 +148,8 @@ Output
 {'summary_accuracy': 0.84}
 ```
 
-This score shows that out of all the samples in our test data, only 84% of summaries passes the given evaluation criteria. Now, **It
-s important to see why is this the case**.
+This score shows that out of all the samples in our test data, only 84% of summaries passes the given evaluation criteria. Now, **It's
+important to see why is this the case**.
 
 Export the sample level scores to pandas dataframe
 
@@ -187,4 +187,4 @@ If you want help with improving and scaling up your AI application using evals.
 
 ## Up Next
 
-- [Evaluate a simple RAG application](rag_eval.md)
\ No newline at end of file
+- [Evaluate a simple RAG application](rag_eval.md)