diff --git a/backend/innercontext/api/routines.py b/backend/innercontext/api/routines.py
index 4cac357..3292ca1 100644
--- a/backend/innercontext/api/routines.py
+++ b/backend/innercontext/api/routines.py
@@ -5,7 +5,7 @@ from uuid import UUID, uuid4
 
 from fastapi import APIRouter, Depends, HTTPException
 from pydantic import BaseModel as PydanticBase
-from sqlmodel import Session, SQLModel, col, select
+from sqlmodel import Field, Session, SQLModel, col, select
 
 from db import get_session
 from innercontext.api.utils import get_or_404
@@ -76,6 +76,8 @@ class SuggestedStep(SQLModel):
     action_notes: Optional[str] = None
     dose: Optional[str] = None
     region: Optional[str] = None
+    why_this_step: Optional[str] = None
+    optional: Optional[bool] = None
 
 
 class SuggestRoutineRequest(SQLModel):
@@ -86,9 +88,16 @@ class SuggestRoutineRequest(SQLModel):
     leaving_home: Optional[bool] = None
 
 
+class RoutineSuggestionSummary(SQLModel):
+    primary_goal: str = ""
+    constraints_applied: list[str] = Field(default_factory=list)
+    confidence: float = 0.0
+
+
 class RoutineSuggestion(SQLModel):
     steps: list[SuggestedStep]
     reasoning: str
+    summary: Optional[RoutineSuggestionSummary] = None
 
 
 class SuggestBatchRequest(SQLModel):
@@ -116,7 +125,17 @@ class BatchSuggestion(SQLModel):
 # ---------------------------------------------------------------------------
 
 
-class _StepOut(PydanticBase):
+class _SingleStepOut(PydanticBase):
+    product_id: Optional[str] = None
+    action_type: Optional[GroomingAction] = None
+    dose: Optional[str] = None
+    region: Optional[str] = None
+    action_notes: Optional[str] = None
+    why_this_step: Optional[str] = None
+    optional: Optional[bool] = None
+
+
+class _BatchStepOut(PydanticBase):
     product_id: Optional[str] = None
     action_type: Optional[GroomingAction] = None
     dose: Optional[str] = None
@@ -124,15 +143,22 @@ class _StepOut(PydanticBase):
     action_notes: Optional[str] = None
 
 
+class _SummaryOut(PydanticBase):
+    primary_goal: str
+    constraints_applied: list[str]
+    confidence: float
+
+
 class _SuggestionOut(PydanticBase):
-    steps: list[_StepOut]
+    steps: list[_SingleStepOut]
     reasoning: str
+    summary: _SummaryOut
 
 
 class _DayPlanOut(PydanticBase):
     date: str
-    am_steps: list[_StepOut]
-    pm_steps: list[_StepOut]
+    am_steps: list[_BatchStepOut]
+    pm_steps: list[_BatchStepOut]
     reasoning: str
 
 
@@ -424,6 +450,8 @@ ZASADY PLANOWANIA:
 - Jeśli krok to produkt: podaj poprawny UUID z listy.
 - Jeśli krok to czynność pielęgnacyjna: product_id = null. Dozwolone akcje są ściśle określone w schemacie (action_type).
 - Nie zwracaj "pustych" kroków: każdy krok musi mieć product_id albo action_type.
+- Pole region uzupełniaj tylko gdy ma znaczenie kliniczne/praktyczne (np. broda, wąsy, okolica oczu, szyja).
+  Dla standardowych kroków pielęgnacji całej twarzy pozostaw region puste.
 
 JAK ROZWIĄZYWAĆ KONFLIKTY:
 - Gdy cel użytkownika koliduje z bezpieczeństwem, wybierz bezpieczeństwo.
@@ -432,6 +460,17 @@ JAK ROZWIĄZYWAĆ KONFLIKTY:
 """
 
 
+_ROUTINES_SINGLE_EXTRA = """\
+DODATKOWE WYMAGANIA DLA TRYBU JEDNEJ RUTYNY:
+- Każdy krok powinien mieć zwięzłe why_this_step (maks. jedno zdanie).
+- Pole optional ustawiaj na true tylko dla kroków niekrytycznych.
+- Uzupełnij summary:
+  - primary_goal: główny cel tej rutyny,
+  - constraints_applied: lista kluczowych ograniczeń zastosowanych przy planowaniu,
+  - confidence: liczba 0-1.
+"""
+
+
 # ---------------------------------------------------------------------------
 # Helper
 # ---------------------------------------------------------------------------
@@ -515,6 +554,7 @@ def suggest_routine(
         "INPUT DATA:\n"
         f"{skin_ctx}\n{grooming_ctx}\n{history_ctx}\n{day_ctx}\n{products_ctx}\n{objectives_ctx}"
         f"{notes_line}\n"
+        f"{_ROUTINES_SINGLE_EXTRA}\n"
         "Zwróć JSON zgodny ze schematem."
     )
 
@@ -545,10 +585,34 @@ def suggest_routine(
             action_notes=s.get("action_notes"),
             dose=s.get("dose"),
             region=s.get("region"),
+            why_this_step=s.get("why_this_step"),
+            optional=s.get("optional"),
         )
         for s in parsed.get("steps", [])
     ]
-    return RoutineSuggestion(steps=steps, reasoning=parsed.get("reasoning", ""))
+
+    summary_raw = parsed.get("summary") or {}
+    confidence_raw = summary_raw.get("confidence", 0)
+    try:
+        confidence = float(confidence_raw)
+    except (TypeError, ValueError):
+        confidence = 0.0
+    confidence = max(0.0, min(1.0, confidence))
+    constraints_applied = summary_raw.get("constraints_applied") or []
+    if not isinstance(constraints_applied, list):
+        constraints_applied = []
+
+    summary = RoutineSuggestionSummary(
+        primary_goal=str(summary_raw.get("primary_goal") or ""),
+        constraints_applied=[str(x) for x in constraints_applied],
+        confidence=confidence,
+    )
+
+    return RoutineSuggestion(
+        steps=steps,
+        reasoning=parsed.get("reasoning", ""),
+        summary=summary,
+    )
 
 
 @router.post("/suggest-batch", response_model=BatchSuggestion)
@@ -624,6 +688,8 @@ def suggest_batch(
                     action_notes=s.get("action_notes"),
                     dose=s.get("dose"),
                     region=s.get("region"),
+                    why_this_step=s.get("why_this_step"),
+                    optional=s.get("optional"),
                 )
             )
         return result
diff --git a/frontend/messages/en.json b/frontend/messages/en.json
index 4cc2be2..35d2c3a 100644
--- a/frontend/messages/en.json
+++ b/frontend/messages/en.json
@@ -171,6 +171,10 @@
   "suggest_errorSave": "Error saving.",
   "suggest_amMorning": "AM (morning)",
   "suggest_pmEvening": "PM (evening)",
+  "suggest_summaryPrimaryGoal": "Primary goal",
+  "suggest_summaryConfidence": "Confidence",
+  "suggest_summaryConstraints": "Constraints",
+  "suggest_stepOptionalBadge": "optional",
 
   "medications_title": "Medications",
   "medications_count": "{count} entries",
diff --git a/frontend/messages/pl.json b/frontend/messages/pl.json
index 597fb52..60524d2 100644
--- a/frontend/messages/pl.json
+++ b/frontend/messages/pl.json
@@ -171,6 +171,10 @@
   "suggest_errorSave": "Błąd podczas zapisywania.",
   "suggest_amMorning": "AM (rano)",
   "suggest_pmEvening": "PM (wieczór)",
+  "suggest_summaryPrimaryGoal": "Główny cel",
+  "suggest_summaryConfidence": "Pewność",
+  "suggest_summaryConstraints": "Ograniczenia",
+  "suggest_stepOptionalBadge": "opcjonalny",
 
   "medications_title": "Leki",
   "medications_count": "{count} wpisów",
diff --git a/frontend/src/lib/types.ts b/frontend/src/lib/types.ts
index 876e31a..18d7fae 100644
--- a/frontend/src/lib/types.ts
+++ b/frontend/src/lib/types.ts
@@ -224,11 +224,20 @@ export interface SuggestedStep {
   action_notes?: string;
   dose?: string;
   region?: string;
+  why_this_step?: string;
+  optional?: boolean;
+}
+
+export interface RoutineSuggestionSummary {
+  primary_goal: string;
+  constraints_applied: string[];
+  confidence: number;
 }
 
 export interface RoutineSuggestion {
   steps: SuggestedStep[];
   reasoning: string;
+  summary?: RoutineSuggestionSummary;
 }
 
 export interface DayPlan {
diff --git a/frontend/src/routes/routines/suggest/+page.svelte b/frontend/src/routes/routines/suggest/+page.svelte
index 8c295a3..e0de468 100644
--- a/frontend/src/routes/routines/suggest/+page.svelte
+++ b/frontend/src/routes/routines/suggest/+page.svelte
@@ -45,7 +45,7 @@
 	function stepMeta(step: SuggestedStep): string {
 		const parts: string[] = [];
 		if (step.dose) parts.push(step.dose);
-		if (step.region) parts.push(step.region);
+		if (step.region && step.region.toLowerCase() !== 'face') parts.push(step.region);
 		if (step.action_notes && !step.action_type) parts.push(step.action_notes);
 		return parts.join(' · ');
 	}
@@ -209,6 +209,20 @@
 						</CardContent>
 					</Card>
 
+					{#if suggestion.summary}
+						<Card class="border-muted bg-muted/30">
+							<CardContent class="space-y-2 pt-4">
+								<p class="text-sm"><span class="font-medium">{m["suggest_summaryPrimaryGoal"]()}:</span> {suggestion.summary.primary_goal || '—'}</p>
+								<p class="text-sm"><span class="font-medium">{m["suggest_summaryConfidence"]()}:</span> {Math.round((suggestion.summary.confidence ?? 0) * 100)}%</p>
+								{#if suggestion.summary.constraints_applied?.length}
+									<p class="text-xs text-muted-foreground">
+										{m["suggest_summaryConstraints"]()}: {suggestion.summary.constraints_applied.join(' · ')}
+									</p>
+								{/if}
+							</CardContent>
+						</Card>
+					{/if}
+
 					<!-- Steps -->
 					<div class="space-y-2">
 						{#each suggestion.steps as step, i (i)}
@@ -217,10 +231,18 @@
 									{i + 1}
 								</span>
 								<div class="min-w-0 flex-1">
-									<p class="text-sm font-medium">{stepLabel(step)}</p>
+									<div class="flex items-center gap-2">
+										<p class="text-sm font-medium">{stepLabel(step)}</p>
+										{#if step.optional}
+											<Badge variant="secondary">{m["suggest_stepOptionalBadge"]()}</Badge>
+										{/if}
+									</div>
 									{#if stepMeta(step)}
 										<p class="text-xs text-muted-foreground">{stepMeta(step)}</p>
 									{/if}
+									{#if step.why_this_step}
+										<p class="text-xs text-muted-foreground italic">{step.why_this_step}</p>
+									{/if}
 								</div>
 							</div>
 						{/each}