@@ -19,13 +19,13 @@ Context-first AI coding for VS Code, Cursor, and others. Free, open-source, and
 
 ## Introduction
 
-Large language models are brilliant, yet mindless pattern matchers. As they lack any properties similar to mental models—they can't _imagine_ how the correct output should look like ahead of filling their context windows on their own. To mitigate this limitation, other tools ask you to put effort into planning—a practice of expanding instructions, so the model can do a better job at finding relevant files. This is a slow, token-hungry hit or miss.
+Large language models are brilliant, yet mindless pattern matchers. As they lack any properties similar to mental models—they can't _imagine_ how the correct output should look like before they start filling their context with files. To mitigate this limitation, other _agentic_ tools ask you to put effort into planning—a practice of expanding instructions, so the model can do a better job with the grep of relevant files. This is a slow, token-hungry hit or miss.
 
-Code Web Chat places context ownership in developer's hands! Guide the model with hand-picked files and get **the best accuracy** by not polluting the context window with tool definitions and endless rambling, **save time** by writing simpler instructions (goodbye markdown files!), **save money** by being token-efficient and not using oversized models, ensure **privacy** by not having to send your whole codebase for external indexing and **security** by not running arbitrary commands.
+Code Web Chat places context ownership in developer's hands! Guide the model with hand-picked files and get **the best accuracy** by not polluting the context window with tool definitions and endless rambling, **save time** by writing simpler instructions (goodbye markdown files!) and never waiting for tool calls, **save money** by not using oversized models, ensure **privacy** by not having to send each request for postprocessing or your whole codebase for external indexing.
 
 **Context-first approach**
 
-Work on real-world codebases with a software engineering mindset. Meet a simple, non-agentic workflow—select files, enter instructions, and send message with your favorite chatbot or a model provider of choice.
+Meet a simple, non-agentic workflow—select files, enter instructions, and send message with your favorite chatbot or a model provider of choice.
 
 > [!TIP]
 > LLMs are pattern matchers—they love examples! Guide the model with context for production-grade code.
@@ -47,7 +47,7 @@ Whenever showing a new, updated, renamed or deleted file...
 Implement a subtract function.
 ```
 
-Once the response is generated, a built-in sophisticated parser extracts code blocks with file edits for one-click changes integration.
+Once the response is generated, a built-in parser extracts code blocks with file edits for a one-click, interactive changes integration.
 
 ## Browser integration