diff --git a/.gitignore b/.gitignore
index 8c06000c..e90fde6a 100644
--- a/.gitignore
+++ b/.gitignore
@@ -14,6 +14,7 @@ Desktop.ini
 .env
 .env.*
 !.env.example
+/config.json
 *.pem
 *.key
 *.crt
diff --git a/apps/backend/cli/utils.py b/apps/backend/cli/utils.py
index b9969020..0e2a7b42 100644
--- a/apps/backend/cli/utils.py
+++ b/apps/backend/cli/utils.py
@@ -15,6 +15,7 @@ if str(_PARENT_DIR) not in sys.path:
     sys.path.insert(0, str(_PARENT_DIR))
 
 from core.auth import get_auth_token, get_auth_token_source
+from core.dependency_validator import validate_platform_dependencies
 
 
 def import_dotenv():
@@ -154,6 +155,9 @@ def validate_environment(spec_dir: Path) -> bool:
     Returns:
         True if valid, False otherwise (with error messages printed)
     """
+    # Validate platform-specific dependencies first (exits if missing)
+    validate_platform_dependencies()
+
     valid = True
 
     # Check for OAuth token (API keys are not supported)
diff --git a/apps/backend/core/dependency_validator.py b/apps/backend/core/dependency_validator.py
new file mode 100644
index 00000000..8517cb36
--- /dev/null
+++ b/apps/backend/core/dependency_validator.py
@@ -0,0 +1,50 @@
+"""
+Dependency Validator
+====================
+
+Validates platform-specific dependencies are installed before running agents.
+"""
+
+import sys
+from pathlib import Path
+
+
+def validate_platform_dependencies() -> None:
+    """
+    Validate that platform-specific dependencies are installed.
+
+    Raises:
+        SystemExit: If required platform-specific dependencies are missing,
+                   with helpful installation instructions.
+    """
+    # Check Windows-specific dependencies
+    if sys.platform == "win32" and sys.version_info >= (3, 12):
+        try:
+            import pywintypes  # noqa: F401
+        except ImportError:
+            _exit_with_pywin32_error()
+
+
+def _exit_with_pywin32_error() -> None:
+    """Exit with helpful error message for missing pywin32."""
+    # Use sys.prefix to detect the virtual environment path
+    # This works for venv and poetry environments
+    venv_activate = Path(sys.prefix) / "Scripts" / "activate"
+
+    sys.exit(
+        "Error: Required Windows dependency 'pywin32' is not installed.\n"
+        "\n"
+        "Auto Claude requires pywin32 on Windows for LadybugDB/Graphiti memory integration.\n"
+        "\n"
+        "To fix this:\n"
+        "1. Activate your virtual environment:\n"
+        f"   {venv_activate}\n"
+        "\n"
+        "2. Install pywin32:\n"
+        "   pip install pywin32>=306\n"
+        "\n"
+        "   Or reinstall all dependencies:\n"
+        "   pip install -r requirements.txt\n"
+        "\n"
+        f"Current Python: {sys.executable}\n"
+    )
diff --git a/apps/backend/integrations/graphiti/queries_pkg/client.py b/apps/backend/integrations/graphiti/queries_pkg/client.py
index c1961484..3808d9d5 100644
--- a/apps/backend/integrations/graphiti/queries_pkg/client.py
+++ b/apps/backend/integrations/graphiti/queries_pkg/client.py
@@ -34,8 +34,25 @@ def _apply_ladybug_monkeypatch() -> bool:
         sys.modules["kuzu"] = real_ladybug
         logger.info("Applied LadybugDB monkeypatch (kuzu -> real_ladybug)")
         return True
-    except ImportError:
-        pass
+    except ImportError as e:
+        logger.debug(f"LadybugDB import failed: {e}")
+        # On Windows with Python 3.12+, provide more specific error details
+        # (pywin32 is only required for Python 3.12+ per requirements.txt)
+        if sys.platform == "win32" and sys.version_info >= (3, 12):
+            # Check if it's the pywin32 error using both name attribute and string match
+            # for robustness across Python versions
+            is_pywin32_error = (
+                (hasattr(e, "name") and e.name in ("pywintypes", "pywin32", "win32api"))
+                or "pywintypes" in str(e)
+                or "pywin32" in str(e)
+            )
+            if is_pywin32_error:
+                logger.error(
+                    "LadybugDB requires pywin32 on Windows. "
+                    "Install with: pip install pywin32>=306"
+                )
+            else:
+                logger.debug(f"Windows-specific import issue: {e}")
 
     # Fall back to native kuzu
     try:
diff --git a/apps/backend/requirements.txt b/apps/backend/requirements.txt
index 59aec7b0..95c8a1ea 100644
--- a/apps/backend/requirements.txt
+++ b/apps/backend/requirements.txt
@@ -10,6 +10,10 @@ tomli>=2.0.0; python_version < "3.11"
 real_ladybug>=0.13.0; python_version >= "3.12"
 graphiti-core>=0.5.0; python_version >= "3.12"
 
+# Windows-specific dependency for LadybugDB/Graphiti
+# pywin32 provides Windows system bindings required by real_ladybug
+pywin32>=306; sys_platform == "win32" and python_version >= "3.12"
+
 # Google AI (optional - for Gemini LLM and embeddings)
 google-generativeai>=0.8.0
 
diff --git a/tests/test_github_pr_review.py b/tests/test_github_pr_review.py
index 25b72fe4..741d69bc 100644
--- a/tests/test_github_pr_review.py
+++ b/tests/test_github_pr_review.py
@@ -101,13 +101,11 @@ def mock_bot_detector(tmp_path):
 class TestPRReviewResult:
     """Test PRReviewResult model."""
 
-    def test_save_and_load(self, temp_github_dir, sample_review_result):
+    @pytest.mark.asyncio
+    async def test_save_and_load(self, temp_github_dir, sample_review_result):
         """Test saving and loading review result."""
         # Save
-        import asyncio
-        asyncio.get_event_loop().run_until_complete(
-            sample_review_result.save(temp_github_dir)
-        )
+        await sample_review_result.save(temp_github_dir)
 
         # Verify file exists
         review_file = temp_github_dir / "pr" / f"review_{sample_review_result.pr_number}.json"
@@ -337,14 +335,11 @@ class TestBotDetectionIntegration:
 class TestOrchestratorSkipLogic:
     """Test orchestrator behavior when bot detection skips."""
 
-    def test_skip_returns_existing_review(self, temp_github_dir, sample_review_result):
+    @pytest.mark.asyncio
+    async def test_skip_returns_existing_review(self, temp_github_dir, sample_review_result):
         """Test that skipping 'Already reviewed' returns existing review."""
-        import asyncio
-
         # Save existing review
-        asyncio.get_event_loop().run_until_complete(
-            sample_review_result.save(temp_github_dir)
-        )
+        await sample_review_result.save(temp_github_dir)
 
         # Simulate the orchestrator logic for "Already reviewed" skip
         skip_reason = "Already reviewed commit abc123"
@@ -466,19 +461,16 @@ class TestPostedFindingsTracking:
         assert sample_review_result.has_posted_findings is True
         assert len(sample_review_result.posted_finding_ids) == 1
 
-    def test_posted_findings_serialization(self, temp_github_dir, sample_review_result):
+    @pytest.mark.asyncio
+    async def test_posted_findings_serialization(self, temp_github_dir, sample_review_result):
         """Test that posted findings are serialized correctly."""
-        import asyncio
-
         # Set posted findings
         sample_review_result.has_posted_findings = True
         sample_review_result.posted_finding_ids = ["finding-001"]
         sample_review_result.posted_at = "2025-01-01T10:00:00"
 
         # Save
-        asyncio.get_event_loop().run_until_complete(
-            sample_review_result.save(temp_github_dir)
-        )
+        await sample_review_result.save(temp_github_dir)
 
         # Load and verify
         loaded = PRReviewResult.load(temp_github_dir, sample_review_result.pr_number)