diff --git a/apps/docs/models.mdx b/apps/docs/models.mdx
index 067c749fb..f13b56c83 100644
--- a/apps/docs/models.mdx
+++ b/apps/docs/models.mdx
@@ -280,7 +280,8 @@ on the old settings, and the next turn (including its sub-agents) uses the new
 ones. Overrides persist for the life of the task, including snapshot resumes,
 and **Reset to defaults** returns every role to the deployment configuration.
 
-You can also just ask the agent — for example "switch to Fable 5 with max
+When a message continues an existing task from the web or a connected chat,
+you can also just ask the agent — for example "switch to Fable 5 with max
 reasoning for the rest of this task". The agent applies the same change
 through its task-management tool, subject to the same allowed-models list.
 
@@ -293,6 +294,11 @@ before launch, so Fast can correct the selection without consuming its launch
 attempt. The chosen model applies to the delegated task just as if it had been
 selected when starting a task from the web app.
 
+In a direct message or channel, include the model and reasoning level in the
+request — for example "use Fable 5 with max reasoning for this task". Fast
+applies that choice to the repository task it delegates. It does not change
+Fast's own orchestration model or the deployment defaults.
+
 A single Fast turn can launch multiple independent tasks, so one request can
 delegate separate workstreams without waiting for each task to finish first.
 Fast still posts a kickoff for every task and keeps repeated identical launch