diff --git a/docs/tasks/NOOK-152/README.md b/docs/tasks/NOOK-152/README.md
new file mode 100644
index 00000000..10ab6183
--- /dev/null
+++ b/docs/tasks/NOOK-152/README.md
@@ -0,0 +1,52 @@
+# NOOK-152 Grafana DatasourceError 반복 알림과 로그 통계 불일치 수정
+
+## 목적
+
+일시적인 Prometheus/Loki 조회 실패가 모든 업무 Alert의 `DatasourceError`로 증폭되는 문제를 줄이고,
+로그 대시보드의 ERROR/WARN 통계를 실제 조회 범위와 일치시킵니다.
+
+## 원인
+
+- Grafana-managed Alert의 `execErrState: Error`는 조회 실패마다 원래 Alert와 독립적인
+  `DatasourceError`를 생성합니다.
+- 기존 정책은 모든 `DatasourceError`를 같은 이름으로 묶어 1시간마다 반복 전송했습니다.
+- datasource provisioning이 Grafana 시작 시 기존 Prometheus/Loki datasource를 삭제한 뒤 다시
+  생성해, 시작 구간의 조회 실패 가능성을 키웠습니다.
+- 로그 stat은 `count_over_time(...[$__range])`를 range 쿼리로 실행해 조회 종료 시점에는 데이터가
+  없어도 과거의 마지막 non-null 값을 표시했습니다.
+
+## 범위
+
+- ERROR/WARN stat을 instant 쿼리로 변경합니다.
+- 업무 Alert의 실행 오류 상태를 Grafana provisioning enum인 `KeepLast`로 변경합니다.
+- Prometheus/Loki 연결 상태를 확인하는 전용 Alert를 추가합니다.
+- `DatasourceError`를 datasource와 원본 규칙별로 그룹화하고 최초 알림을 2분 지연하며 반복 주기를
+  6시간으로 분리합니다.
+- datasource 삭제 후 재생성을 제거합니다.
+- Grafana 시작 전 Prometheus/Loki readiness를 최대 60초 확인합니다. 제한 시간 뒤에는 진단을 위해
+  Grafana를 시작합니다.
+
+## 제외 범위
+
+- 애플리케이션 로그 레벨 또는 로그 포맷 변경
+- dev API 기능/API 계약 변경
+- live 환경 Alert 임계치 도입
+
+## 성공 기준
+
+- 조회 범위에 ERROR/WARN 로그가 없으면 stat이 0을 표시합니다.
+- 일시적 datasource 조회 실패가 모든 업무 Alert의 `DatasourceError`로 확산되지 않습니다.
+- 2분 이상 지속되는 Prometheus/Loki 실행 오류는 전용 규칙의 `DatasourceError`로 식별됩니다.
+- alert provisioning YAML, dashboard JSON, Docker Compose 구성이 유효합니다.
+
+## 검증
+
+```shell
+ruby -e 'require "yaml"; Dir["ops/**/*.yml"].each { |file| YAML.load_file(file) }'
+jq empty ops/monitoring/grafana/dashboards/*.json
+docker compose -f ops/monitoring/docker-compose.yml config
+./gradlew check
+```
+
+ops VM 반영 후 Grafana rules API에서 모든 규칙의 health/state를 확인하고, Loki와 Prometheus의
+`vector(1)` 쿼리 및 로그 stat의 instant 쿼리 결과를 직접 비교합니다.
diff --git a/ops/monitoring/docker-compose.yml b/ops/monitoring/docker-compose.yml
index 9ecf0447..cad34e25 100644
--- a/ops/monitoring/docker-compose.yml
+++ b/ops/monitoring/docker-compose.yml
@@ -29,6 +29,9 @@ services:
   grafana:
     image: grafana/grafana:latest
     container_name: nook-ops-grafana
+    entrypoint:
+      - /bin/sh
+      - /etc/grafana/startup/wait-for-datasources.sh
     depends_on:
       - prometheus
       - loki
@@ -41,6 +44,7 @@ services:
       - "127.0.0.1:3000:3000"
     volumes:
       - grafana-data:/var/lib/grafana
+      - ./grafana/startup:/etc/grafana/startup:ro
       - ./grafana/provisioning:/etc/grafana/provisioning:ro
       - ./grafana/dashboards:/var/lib/grafana/dashboards:ro
     restart: unless-stopped
diff --git a/ops/monitoring/grafana/dashboards/nook-dev-logs.json b/ops/monitoring/grafana/dashboards/nook-dev-logs.json
index 669a75a7..002871b9 100644
--- a/ops/monitoring/grafana/dashboards/nook-dev-logs.json
+++ b/ops/monitoring/grafana/dashboards/nook-dev-logs.json
@@ -158,8 +158,8 @@
             "uid": "loki"
           },
           "editorMode": "code",
-          "expr": "sum(count_over_time({env=\"dev\", job=\"nook-api\", level=\"ERROR\"}[$__range]))",
-          "queryType": "range",
+          "expr": "sum(count_over_time({env=\"dev\", job=\"nook-api\", level=\"ERROR\"}[$__range])) or on() vector(0)",
+          "queryType": "instant",
           "refId": "A"
         }
       ],
@@ -220,8 +220,8 @@
             "uid": "loki"
           },
           "editorMode": "code",
-          "expr": "sum(count_over_time({env=\"dev\", job=\"nook-api\", level=\"WARN\"}[$__range]))",
-          "queryType": "range",
+          "expr": "sum(count_over_time({env=\"dev\", job=\"nook-api\", level=\"WARN\"}[$__range])) or on() vector(0)",
+          "queryType": "instant",
           "refId": "A"
         }
       ],
diff --git a/ops/monitoring/grafana/provisioning/alerting/nook-datasource-alerts.yml b/ops/monitoring/grafana/provisioning/alerting/nook-datasource-alerts.yml
new file mode 100644
index 00000000..02e8bf5a
--- /dev/null
+++ b/ops/monitoring/grafana/provisioning/alerting/nook-datasource-alerts.yml
@@ -0,0 +1,155 @@
+apiVersion: 1
+
+groups:
+  - orgId: 1
+    name: nook-datasource-alerts
+    folder: Nook
+    interval: 1m
+    rules:
+      - uid: nook_prometheus_datasource_unavailable
+        title: Prometheus datasource unavailable
+        condition: C
+        data:
+          - refId: A
+            datasourceUid: prometheus
+            relativeTimeRange:
+              from: 300
+              to: 0
+            model:
+              datasource:
+                type: prometheus
+                uid: prometheus
+              editorMode: code
+              expr: vector(1)
+              instant: true
+              intervalMs: 1000
+              maxDataPoints: 43200
+              refId: A
+          - refId: B
+            datasourceUid: __expr__
+            relativeTimeRange:
+              from: 300
+              to: 0
+            model:
+              datasource:
+                type: __expr__
+                uid: __expr__
+              expression: A
+              intervalMs: 1000
+              maxDataPoints: 43200
+              reducer: last
+              refId: B
+              type: reduce
+          - refId: C
+            datasourceUid: __expr__
+            relativeTimeRange:
+              from: 300
+              to: 0
+            model:
+              conditions:
+                - evaluator:
+                    params:
+                      - 1
+                    type: lt
+                  operator:
+                    type: and
+                  query:
+                    params:
+                      - C
+                  reducer:
+                    params: []
+                    type: last
+                  type: query
+              datasource:
+                type: __expr__
+                uid: __expr__
+              expression: B
+              intervalMs: 1000
+              maxDataPoints: 43200
+              refId: C
+              type: threshold
+        noDataState: Alerting
+        execErrState: Error
+        for: 2m
+        annotations:
+          summary: Grafana에서 Prometheus datasource에 연결할 수 없습니다.
+          description: Prometheus 조회가 2분 이상 실패했습니다. Grafana와 Prometheus의 컨테이너 상태 및 Docker DNS를 확인하세요.
+        labels:
+          env: ops
+          service: prometheus
+          severity: warning
+        isPaused: false
+
+      - uid: nook_loki_datasource_unavailable
+        title: Loki datasource unavailable
+        condition: C
+        data:
+          - refId: A
+            datasourceUid: loki
+            relativeTimeRange:
+              from: 300
+              to: 0
+            model:
+              datasource:
+                type: loki
+                uid: loki
+              editorMode: code
+              expr: vector(1)
+              intervalMs: 1000
+              maxDataPoints: 43200
+              queryType: range
+              refId: A
+          - refId: B
+            datasourceUid: __expr__
+            relativeTimeRange:
+              from: 300
+              to: 0
+            model:
+              datasource:
+                type: __expr__
+                uid: __expr__
+              expression: A
+              intervalMs: 1000
+              maxDataPoints: 43200
+              reducer: last
+              refId: B
+              type: reduce
+          - refId: C
+            datasourceUid: __expr__
+            relativeTimeRange:
+              from: 300
+              to: 0
+            model:
+              conditions:
+                - evaluator:
+                    params:
+                      - 1
+                    type: lt
+                  operator:
+                    type: and
+                  query:
+                    params:
+                      - C
+                  reducer:
+                    params: []
+                    type: last
+                  type: query
+              datasource:
+                type: __expr__
+                uid: __expr__
+              expression: B
+              intervalMs: 1000
+              maxDataPoints: 43200
+              refId: C
+              type: threshold
+        noDataState: Alerting
+        execErrState: Error
+        for: 2m
+        annotations:
+          summary: Grafana에서 Loki datasource에 연결할 수 없습니다.
+          description: Loki 조회가 2분 이상 실패했습니다. Grafana와 Loki의 컨테이너 상태 및 Docker DNS를 확인하세요.
+        labels:
+          env: ops
+          service: loki
+          severity: warning
+        isPaused: false
diff --git a/ops/monitoring/grafana/provisioning/alerting/nook-dev-api-errors.yml b/ops/monitoring/grafana/provisioning/alerting/nook-dev-api-errors.yml
index d096ae3f..b8dab37e 100644
--- a/ops/monitoring/grafana/provisioning/alerting/nook-dev-api-errors.yml
+++ b/ops/monitoring/grafana/provisioning/alerting/nook-dev-api-errors.yml
@@ -69,7 +69,7 @@ groups:
               refId: C
               type: threshold
         noDataState: OK
-        execErrState: Error
+        execErrState: KeepLast
         for: 1m
         annotations:
           summary: dev API에서 ERROR 로그가 감지됐습니다.
diff --git a/ops/monitoring/grafana/provisioning/alerting/nook-dev-core-alerts.yml b/ops/monitoring/grafana/provisioning/alerting/nook-dev-core-alerts.yml
index d6948142..ac279f05 100644
--- a/ops/monitoring/grafana/provisioning/alerting/nook-dev-core-alerts.yml
+++ b/ops/monitoring/grafana/provisioning/alerting/nook-dev-core-alerts.yml
@@ -64,7 +64,7 @@ groups:
               refId: C
               type: threshold
         noDataState: Alerting
-        execErrState: Error
+        execErrState: KeepLast
         for: 2m
         annotations:
           summary: dev API target이 응답하지 않습니다.
@@ -133,7 +133,7 @@ groups:
               refId: C
               type: threshold
         noDataState: Alerting
-        execErrState: Error
+        execErrState: KeepLast
         for: 5m
         annotations:
           summary: dev MySQL exporter target이 응답하지 않습니다.
@@ -202,7 +202,7 @@ groups:
               refId: C
               type: threshold
         noDataState: Alerting
-        execErrState: Error
+        execErrState: KeepLast
         for: 5m
         annotations:
           summary: dev node exporter target이 응답하지 않습니다.
@@ -271,7 +271,7 @@ groups:
               refId: C
               type: threshold
         noDataState: OK
-        execErrState: Error
+        execErrState: KeepLast
         for: 5m
         annotations:
           summary: dev API의 HTTP 5xx 응답이 증가했습니다.
@@ -340,7 +340,7 @@ groups:
               refId: C
               type: threshold
         noDataState: OK
-        execErrState: Error
+        execErrState: KeepLast
         for: 10m
         annotations:
           summary: dev API의 HTTP p95 latency가 높습니다.
@@ -409,7 +409,7 @@ groups:
               refId: C
               type: threshold
         noDataState: OK
-        execErrState: Error
+        execErrState: KeepLast
         for: 15m
         annotations:
           summary: dev VM 루트 디스크 사용률이 80%를 넘었습니다.
@@ -478,7 +478,7 @@ groups:
               refId: C
               type: threshold
         noDataState: OK
-        execErrState: Error
+        execErrState: KeepLast
         for: 5m
         annotations:
           summary: dev VM 루트 디스크 사용률이 90%를 넘었습니다.
@@ -547,7 +547,7 @@ groups:
               refId: C
               type: threshold
         noDataState: OK
-        execErrState: Error
+        execErrState: KeepLast
         for: 10m
         annotations:
           summary: dev VM 메모리 사용률이 90%를 넘었습니다.
@@ -616,7 +616,7 @@ groups:
               refId: C
               type: threshold
         noDataState: OK
-        execErrState: Error
+        execErrState: KeepLast
         for: 3m
         annotations:
           summary: dev API의 DB connection pool이 고갈되고 있습니다.
@@ -685,7 +685,7 @@ groups:
               refId: C
               type: threshold
         noDataState: OK
-        execErrState: Error
+        execErrState: KeepLast
         for: 0s
         annotations:
           summary: dev API에서 DB connection 획득 timeout이 발생했습니다.
diff --git a/ops/monitoring/grafana/provisioning/alerting/notification-policies.yml b/ops/monitoring/grafana/provisioning/alerting/notification-policies.yml
index 78c5830c..699513f5 100644
--- a/ops/monitoring/grafana/provisioning/alerting/notification-policies.yml
+++ b/ops/monitoring/grafana/provisioning/alerting/notification-policies.yml
@@ -9,3 +9,15 @@ policies:
     group_wait: 30s
     group_interval: 5m
     repeat_interval: 1h
+    routes:
+      - receiver: slack-nook-alerts-v2
+        object_matchers:
+          - - alertname
+            - =
+            - DatasourceError
+        group_by:
+          - datasource_uid
+          - rulename
+        group_wait: 2m
+        group_interval: 10m
+        repeat_interval: 6h
diff --git a/ops/monitoring/grafana/provisioning/datasources/datasources.yml b/ops/monitoring/grafana/provisioning/datasources/datasources.yml
index ddc6876f..237a2297 100644
--- a/ops/monitoring/grafana/provisioning/datasources/datasources.yml
+++ b/ops/monitoring/grafana/provisioning/datasources/datasources.yml
@@ -1,11 +1,5 @@
 apiVersion: 1
 
-deleteDatasources:
-  - name: Prometheus
-    orgId: 1
-  - name: Loki
-    orgId: 1
-
 datasources:
   - name: Prometheus
     type: prometheus
diff --git a/ops/monitoring/grafana/startup/wait-for-datasources.sh b/ops/monitoring/grafana/startup/wait-for-datasources.sh
new file mode 100755
index 00000000..29a70c56
--- /dev/null
+++ b/ops/monitoring/grafana/startup/wait-for-datasources.sh
@@ -0,0 +1,20 @@
+#!/bin/sh
+
+set -eu
+
+max_attempts=30
+attempt=1
+
+while [ "$attempt" -le "$max_attempts" ]; do
+  if wget -q -T 2 -O /dev/null http://prometheus:9090/-/ready \
+    && wget -q -T 2 -O /dev/null http://loki:3100/ready; then
+    exec /run.sh
+  fi
+
+  echo "Waiting for Prometheus and Loki readiness (${attempt}/${max_attempts})" >&2
+  attempt=$((attempt + 1))
+  sleep 2
+done
+
+echo "Datasource readiness wait timed out; starting Grafana for diagnostics" >&2
+exec /run.sh