Update instructions for steering agent conversations

Clarified instructions on interacting with the agent while it is processing a task, emphasizing the absence of a separate instruction queue and how to steer the conversation.

The origianl was vauage as to how to actually steer it, and new to the CLI users might not understand. Also, queuing was not explained as it was assumed to be naturally understood. Not so. This should smoothing the instructions over without undue weight of words.

Author: Brenduns

content/copilot/how-tos/copilot-cli/use-copilot-cli-agents/steer-agents.md

@@ -14,7 +14,9 @@ docsTeamMetrics:
 
 ## Steer the conversation while {% data variables.product.prodname_copilot_short %} is thinking
 
-You can interact with {% data variables.product.prodname_copilot_short %} while it's thinking. Send follow-up messages to steer the conversation in a different direction, or queue additional instructions for {% data variables.product.prodname_copilot_short %} to process after it finishes its current response.
+While {% data variables.product.prodname_copilot_short %} is actively working on a task, you can enter a new prompt at any time. Any input you send while the agent is thinking is treated as steering and is considered in the context of the current task.
+
+There is no separate instruction queue. To queue additional instructions, simply enter another prompt while {% data variables.product.prodname_copilot_short %} is running. {% data variables.product.prodname_copilot_short %} processes each message in order as part of the active task.
 
 Steering lets you: