diff --git a/.overhaul/APPLY.sh b/.overhaul/APPLY.sh
index 6ba8312..06aefa0 100755
--- a/.overhaul/APPLY.sh
+++ b/.overhaul/APPLY.sh
@@ -199,7 +199,7 @@ JSON
 JSON
   change 'openadapt-desktop: description and website' \
     gh api --method PATCH "repos/$ORG/openadapt-desktop" --input - <<'JSON'
-{"description": "The OpenAdapt app. Record a task once, watch it run, see what it entered, and decide what happens when a run stops.", "homepage": "https://openadapt.ai/platform/desktop"}
+{"description": "The OpenAdapt app. Record a task, watch it run, see what it entered, and decide what happens when a run stops.", "homepage": "https://openadapt.ai/platform/desktop"}
 JSON
   change 'openadapt-desktop: topics' \
     gh api --method PUT "repos/$ORG/openadapt-desktop/topics" --input - <<'JSON'
@@ -441,7 +441,7 @@ verify_github() {
     audit-trail,automation-from-demonstration,browser-automation,citrix,computer-use,demonstration-compiler,desktop-automation,deterministic-replay,effect-verification,emr,gui-automation,healthcare-automation,human-in-the-loop,local-first,python,rdp,robotic-process-automation,rpa,ui-automation,workflow-automation \
     gh api "repos/$ORG/openadapt-flow/topics" --jq '.names | sort | join(",")'
   expect 'openadapt-desktop: description' \
-    'The OpenAdapt app. Record a task once, watch it run, see what it entered, and decide what happens when a run stops.' \
+    'The OpenAdapt app. Record a task, watch it run, see what it entered, and decide what happens when a run stops.' \
     gh api "repos/$ORG/openadapt-desktop" --jq '.description // ""'
   expect 'openadapt-desktop: website' \
     https://openadapt.ai/platform/desktop \
diff --git a/profile/README.md b/profile/README.md
index affa29c..a0ce02f 100644
--- a/profile/README.md
+++ b/profile/README.md
@@ -63,7 +63,7 @@ Hand the workflow to us, or run the open-source engine yourself.
 Tell us about a task your team repeats:
 [discuss your workflow](https://openadapt.ai/book).
 
-1. You show us the task once, on your own system.
+1. A person or an agent shows the task on your own system.
 2. We build the automation and test it with your own cases before it goes
    live.
 3. We keep it working. When a screen changes, we propose a fix, and a person
diff --git a/repository-lifecycle.yml b/repository-lifecycle.yml
index 711083a..eca0adc 100644
--- a/repository-lifecycle.yml
+++ b/repository-lifecycle.yml
@@ -84,8 +84,8 @@ public_metadata:
         - robotic-process-automation
     openadapt-desktop:
       description: >-
-        The OpenAdapt app. Record a task once, watch it run, see what it
-        entered, and decide what happens when a run stops.
+        The OpenAdapt app. Record a task, watch it run, see what it entered,
+        and decide what happens when a run stops.
       homepage: https://openadapt.ai/platform/desktop
       topics:
         - automation-from-demonstration