Spelling fixes

docs-site/content/kagent/0.x/examples/slack-a2a.md

@@ -365,7 +365,7 @@ Now let's open the kagent UI and try chatting with the agent. Let's ask the agen
 Can you show me all deployments in my cluster and send it to Slack?
 ```
 
-The agent will run the tools it needs to run and finally caall the `send_message_to_slack` tool to send a message to Slack:
+The agent will run the tools it needs to run and finally call the `send_message_to_slack` tool to send a message to Slack:
 
 ![Sending message to Slack](/images/slack-a2a/send-to-slack.png)
 

docs-site/content/kagent/0.x/getting-started/local-development.md

@@ -169,7 +169,7 @@ The agent has access to the `add` tool as it specified in the response to the us
 
 Now let's deploy the project to a Kubernetes cluster. We'll use the `kagent deploy` command to deploy the agent and MCP servers to a Kubernetes cluster. Make sure you have a Kubernetes cluster and kagent installed in it. 
 
-We'll preprate a `.env.production` file and include the OpenAI API key in it:
+We'll prepare a `.env.production` file and include the OpenAI API key in it:
 
 ```shell
 cat << EOF > .env.production

src/blogContent/inside-kagent-oss-ent-ai-meshes.mdx

@@ -104,7 +104,7 @@ Key pieces to the puzzle include:
 
 This approach empowers both open source and enterprise teams to compose, scale, and govern agent-driven systems—without the complexity and risk of DIY networking, security, and discovery.
 
-One last thing to leave you with before moving on is you may have noticed in the **Traffic Management** bullet point that it says “L8”. With Agent Mesh, an important realization came out - what about the context layer? Agentic Workloads are all about semantic reasoning, which is different form the traditional/syntactic approach. With semantic workflows, a person/agent/bot is asking multiple questions to an Agent and getting a responses in a collected format. What that translates to is any time you ask an LLM several questions via an Agent or an AI dashboard (think Antropics UI, ChatGPT, Geminis UI, etc.), it’s looking at the questions and saying to itself "Are these related?", and the response you get is based on the decision that was made (e.g - are all of these, in fact, related?). The way that the whole process is done from a semantic perspective is that it converts the data to prompt embeddings (e.g - Vector). The embeddings are how LLMs understand the information being passed in. It’s like how a computer understands binary.
+One last thing to leave you with before moving on is you may have noticed in the **Traffic Management** bullet point that it says “L8”. With Agent Mesh, an important realization came out - what about the context layer? Agentic Workloads are all about semantic reasoning, which is different form the traditional/syntactic approach. With semantic workflows, a person/agent/bot is asking multiple questions to an Agent and getting a responses in a collected format. What that translates to is any time you ask an LLM several questions via an Agent or an AI dashboard (think Anthropic's UI, ChatGPT, Gemini's UI, etc.), it’s looking at the questions and saying to itself "Are these related?", and the response you get is based on the decision that was made (e.g - are all of these, in fact, related?). The way that the whole process is done from a semantic perspective is that it converts the data to prompt embeddings (e.g - Vector). The embeddings are how LLMs understand the information being passed in. It’s like how a computer understands binary.
 
 
 ## Why It Matters: Algorithmic and Market Shifts

src/blogContent/kagent-celebrating-100-days.mdx

@@ -77,7 +77,7 @@ Kagent was featured in KCD Texas keynote along with Headlamp, AI model pack and
 ### 🇬🇧London DevOps Meetup May 2025
 Denys Vasyliev presented using kagent for his custom controllers of Kubernetes and MCP servers.
 
-![LinkedIn post from Tor H. around London Devops Meetup with Denys Vasyliev speaking there](/images/blog/100days/London-devops-meetup.png)
+![LinkedIn post from Tor H. around London DevOps Meetup with Denys Vasyliev speaking there](/images/blog/100days/London-devops-meetup.png)
 
 ### 🇨🇳KubeCon China 2025
 The excitement for kagent crossed continents as we shared it with the cloud native community in China.