diff --git a/docs/ai/usage-tokens.md b/docs/ai/usage-tokens.md
index 152efad..e3bb8ea 100644
--- a/docs/ai/usage-tokens.md
+++ b/docs/ai/usage-tokens.md
@@ -65,15 +65,35 @@ Think of each model as a different "speed and cost" setting. Some models are che
 ## Chat Modes And Cost (Plain Language)
 Copilot chat has four modes. The lighter the mode, the less work you ask it to do.
 
-Ask: Questions, summaries, or explanations. Example: "Summarize this file in 5 bullets and list 2 risks."
+Ask: Questions, summaries, or explanations.
 
-Edit: Small, targeted changes with clear constraints. Example: "Update this function to return nil on empty input. Keep behavior the same otherwise."
+Example prompt:
+```text
+Summarize this file in 5 bullets and list 2 risks.
+```
 
-Plan: Get steps before edits. Example: "Give me a 5-step plan to refactor this module. Wait for approval before edits."
+Edit: Small, targeted changes with clear constraints.
 
-Agent: Multi-step work across files or tools. Example: "Refactor these two files, update tests, run the test task, and summarize results."
+Example prompt:
+```text
+Update this function to return nil on empty input. Keep behavior the same otherwise.
+```
 
-#### Example: Choosing A Model
+Plan: Get steps before edits.
+
+Example prompt:
+```text
+Give me a 5-step plan to refactor this module. Wait for approval before edits.
+```
+
+Agent: Multi-step work across files or tools.
+
+Example prompt:
+```text
+Refactor these two files, update tests, run the test task, and summarize results.
+```
+
+### Example: Choosing A Model
 - Task: "Summarize this file in 5 bullets." Use a 0.33x or 1x model.
 - Task: "Refactor three files and update tests." Start with a 1x model. Move to 3x only if the 1x model fails.
 - Task: "Explain a confusing production issue with lots of context." Start with 1x, and only move up if needed.
@@ -149,11 +169,13 @@ If each step is done with a 3x model and a growing chat context, your token use
 ### Use The Right Chat Mode
 Using the lightest chat mode for the job keeps outputs smaller and cheaper.
 
-Example:
-Ask: "Summarize this file in 5 bullets."
-Plan: "Give me a 5-step plan to refactor this module. Wait for approval."
-Edit: "Update this function to handle empty input. Keep behavior the same otherwise."
-Agent: "Refactor these two files, update tests, and summarize results."
+Example prompts:
+```text
+Ask: Summarize this file in 5 bullets.
+Plan: Give me a 5-step plan to refactor this module. Wait for approval.
+Edit: Update this function to handle empty input. Keep behavior the same otherwise.
+Agent: Refactor these two files, update tests, and summarize results.
+```
 
 ## Quick Checklist
 - Is the request specific and scoped?