diff --git a/frontend/src/components/modal/TagPanel.vue b/frontend/src/components/modal/TagPanel.vue
index 38febe9..4f0d335 100644
--- a/frontend/src/components/modal/TagPanel.vue
+++ b/frontend/src/components/modal/TagPanel.vue
@@ -86,7 +86,11 @@ async function onNavigate(tag) {
 // Return focus to the tag input after a suggestion is accepted (from the
 // Suggestions panel or the autocomplete dropdown) so the operator can keep
 // typing the next tag without re-clicking the field (operator-asked 2026-06-08).
+// Exposed so a host surface (the Explore workspace) can re-focus the field when
+// it swaps the focused image, without re-clicking. The field's own mobile guard
+// (TagAutocomplete) is preserved.
 function focusTagInput() { tagInputRef.value?.focus?.() }
+defineExpose({ focusTagInput })
 
 async function onRemove(tagId) {
   errorMsg.value = null
diff --git a/frontend/src/views/ExploreView.vue b/frontend/src/views/ExploreView.vue
index f46fec0..34e3630 100644
--- a/frontend/src/views/ExploreView.vue
+++ b/frontend/src/views/ExploreView.vue
@@ -98,7 +98,10 @@
 
         <!-- RIGHT: the modal's tag rail, hosted on the anchor. -->
         <aside class="fc-ex__rail" aria-label="Tags for the focused image">
-          <TagPanel v-if="store.currentImageId != null" :host="store" />
+          <TagPanel
+            v-if="store.currentImageId != null"
+            ref="tagPanelRef" :host="store"
+          />
         </aside>
       </div>
     </template>
@@ -106,7 +109,7 @@
 </template>
 
 <script setup>
-import { computed, onMounted, onUnmounted, ref, watch } from 'vue'
+import { computed, nextTick, onMounted, onUnmounted, ref, watch } from 'vue'
 import { useRoute, useRouter } from 'vue-router'
 import { useApi } from '../composables/useApi.js'
 import { useExploreStore } from '../stores/explore.js'
@@ -125,6 +128,16 @@ const modal = useModalStore()
 const anchorId = computed(() => route.params.imageId || null)
 const seeding = ref(false)
 const seedError = ref(null)
+const tagPanelRef = ref(null)
+
+// Auto-focus the tag input whenever the focused image changes (seed + every
+// walk) so tagging needs no extra click — the whole point of the workspace
+// (operator-asked 2026-06-26). Reuses TagPanel/TagAutocomplete's focus, which
+// keeps its own mobile guard (no soft-keyboard pop on touch).
+watch(
+  () => store.currentImageId,
+  (id) => { if (id != null) nextTick(() => tagPanelRef.value?.focusTagInput?.()) },
+)
 
 // The route is the source of truth. With an anchor, walk it; without one (the
 // bare /explore nav entry) seed a RANDOM image so the tab kick-starts a rabbit