Replace our with the

Author: ajosh0504

docs/20-mongodb-atlas/1-setup.mdx

@@ -6,7 +6,7 @@ If you are doing this lab as part of a MongoDB GenAI Developer Day, at this poin
 If you don't have a cluster yet, follow the steps below to create one.
 :::
 
-In this lab, you will learn how to use MongoDB Atlas as a knowledge base as well as a memory provider for an AI agent that can help you understand technical documentation.
+In this lab, you will learn how to use MongoDB Atlas as a knowledge base as well as a memory provider to build an AI agent for a technical documentation website.
 
 To use MongoDB Atlas, you will need to create an account, a free cluster and obtain the connection string to connect to your cluster. Follow these steps to get set up:
 

docs/40-agent-tools/2-import-data.mdx

@@ -10,7 +10,7 @@ The documentation agent has two tools- a vector search tool to retrieve informat
 
 Let's import the data required by these tools into two MongoDB collections. This is as simple as making a `POST` request to a serverless function that we have created for you.
 
-Run the cells under the **Step 2: Import data** section in the notebook to import the data required by our agent's tools, into MongoDB collections.
+Run the cells under the **Step 2: Import data** section in the notebook to import the data required by the agent's tools, into MongoDB collections.
 
 To verify that the data has been imported into your MongoDB cluster, navigate to the **Overview** page in the Atlas UI. In the **Clusters section**, select your cluster and click **Browse collections**.
 

docs/50-create-agent/1-concepts.mdx

@@ -5,7 +5,7 @@ Here is a quick overview of concepts that you will come across in this section o
 
 ## Creating agents using LangGraph
 
-In this lab, we will use LangGraph by LangChain to orchestrate a technical documentation agent. LangGraph allows you to model agentic systems as graphs. Graphs in LangGraph have the following core features:
+In this lab, we will use LangGraph by LangChain to orchestrate an AI agen for a technical documentation website. LangGraph allows you to model agentic systems as graphs. Graphs in LangGraph have the following core features:
 
 ### State
 Each graph in has a state which is a shared data structure that all the nodes can access and make updates to. You can define custom attributes within the state depending on what parameters you want to track across the nodes of the graph.

docs/50-create-agent/2-define-graph-state.mdx

@@ -1,5 +1,5 @@
 # 👐 Define graph state
 
-Let's start by defining the state of our agent's graph.
+Let's start by defining the state of the agent's graph.
 
-Run the cells under the **Step 5: Define graph state** section in the notebook to define the state of the graph for the documentation agent.
+Run the cells under the **Step 5: Define graph state** section in the notebook to define the graph state for the AI agent.

docs/50-create-agent/3-instantiate-llm.mdx

@@ -1,8 +1,8 @@
 # 👐 Instantiate the LLM
 
-Now let's instantiate the LLM that will serve as the "brain" of our agent, and give it access to the tools we defined previously. 
+Now let's instantiate the LLM that will serve as the "brain" of the agent, and give it access to the tools we defined previously. 
 
-Fill in any `<CODE_BLOCK_N>` placeholders and run the cells under the **Step 6: Instantiate the LLM** section in the notebook to initialize the LLM for our agent and give it access to tools.
+Fill in any `<CODE_BLOCK_N>` placeholders and run the cells under the **Step 6: Instantiate the LLM** section in the notebook to initialize the LLM for the agent and give it access to tools.
 
 The answers for code blocks in this section are as follows:
 

docs/50-create-agent/4-define-graph-nodes.mdx

@@ -1,6 +1,6 @@
 # 👐 Define graph nodes
 
-Let's define the nodes of our graph. Our agent will have two nodes- an agent node and a tool node. 
+Let's define the nodes of the graph. The agent will have two nodes- an agent node and a tool node. 
 
 Fill in any `<CODE_BLOCK_N>` placeholders and run the cells under the **Step 7: Define graph nodes** section in the notebook to define the nodes of the graph.
 

docs/50-create-agent/5-define-conditional-edges.mdx

@@ -2,4 +2,4 @@
 
 Edges in a LangGraph graph can be fixed or conditional. For conditional edges, we need a routing function to conditionally route the workflow to different nodes.
 
-Run the cells under the **Step 8: Define conditional edges** section in the notebook to define the routing function for the one conditional edge in our graph.
+Run the cells under the **Step 8: Define conditional edges** section in the notebook to define the routing function for the one conditional edge in the graph.

docs/50-create-agent/6-build-and-execute-graph.mdx

@@ -1,6 +1,6 @@
 # 👐 Build and execute the graph
 
-Now that we have defined the nodes and edges of the graph, let's put the graph together and execute it to ensure that our agent is working as expected. 
+Now that we have defined the nodes and edges of the graph, let's put the graph together and execute it to ensure that the agent is working as expected. 
 
 Fill in any `<CODE_BLOCK_N>` placeholders and run the cells under the **Step 9: Build the graph** and **Step 10: Execute the graph** sections in the notebook to build and execute the graph.
 

docs/60-adding-memory/2-adding-memory.mdx

@@ -1,8 +1,8 @@
 # 👐 Add memory to the agent
 
-The final step in this lab is to add conversational message history as a form of memory for our agent. 
+The final step in this lab is to add conversational message history as a form of memory for the agent. 
 
-Fill in any `<CODE_BLOCK_N>` placeholders and run the cells under the **Step 11: Add memory to the agent** section in the notebook to add memory to our documentation agent.
+Fill in any `<CODE_BLOCK_N>` placeholders and run the cells under the **Step 11: Add memory to the agent** section in the notebook to add memory to the agent.
 
 The answers for code blocks in this section are as follows: