diff --git a/ansible/roles/monitoring/defaults/main.yml b/ansible/roles/monitoring/defaults/main.yml
index ec9d369526..8a5929c76a 100644
--- a/ansible/roles/monitoring/defaults/main.yml
+++ b/ansible/roles/monitoring/defaults/main.yml
@@ -1,12 +1,47 @@
 ---
+# Project paths and naming
 monitoring_project_dir: /opt/monitoring
-monitoring_loki_image: grafana/loki:3.0.0
-monitoring_promtail_image: grafana/promtail:3.0.0
-monitoring_grafana_image: grafana/grafana:12.3.1
+monitoring_compose_project_name: devops-monitoring
+
+# Images and versions
+loki_version: "3.0.0"
+promtail_version: "3.0.0"
+grafana_version: "12.3.1"
+prometheus_version: "3.9.0"
+monitoring_loki_image: "grafana/loki:{{ loki_version }}"
+monitoring_promtail_image: "grafana/promtail:{{ promtail_version }}"
+monitoring_grafana_image: "grafana/grafana:{{ grafana_version }}"
+
+# App image (reuse web app naming conventions when available)
+monitoring_app_image: "{{ web_app_docker_image | default((dockerhub_username | default('your_dockerhub_username')) ~ '/devops-info-service') }}"
+monitoring_app_tag: "{{ web_app_docker_tag | default(docker_tag | default('latest')) }}"
+
+# Ports
 monitoring_loki_port: 3100
 monitoring_promtail_port: 9080
 monitoring_grafana_port: 3000
+prometheus_port: 9090
+monitoring_app_port: 8000
+monitoring_app_internal_port: 8000
+
+# Retention and scrape behavior
 monitoring_retention_period: 168h
+prometheus_retention_days: 15
+prometheus_retention_size: "10GB"
+prometheus_scrape_interval: "15s"
+
+# Grafana auth
 monitoring_grafana_admin_user: admin
 monitoring_grafana_admin_password: change-me-in-vault
-monitoring_compose_project_name: devops-monitoring
+
+# Scrape targets for prometheus.yml.j2 template
+prometheus_targets:
+  - job: "prometheus"
+    targets: ["localhost:9090"]
+  - job: "loki"
+    targets: ["loki:3100"]
+  - job: "grafana"
+    targets: ["grafana:3000"]
+  - job: "app"
+    targets: ["app-python:8000"]
+    path: "/metrics"
diff --git a/ansible/roles/monitoring/files/grafana-app-dashboard.json b/ansible/roles/monitoring/files/grafana-app-dashboard.json
new file mode 100644
index 0000000000..2f4ceb99c8
--- /dev/null
+++ b/ansible/roles/monitoring/files/grafana-app-dashboard.json
@@ -0,0 +1,436 @@
+{
+  "annotations": {
+    "list": [
+      {
+        "builtIn": 1,
+        "datasource": {
+          "type": "grafana",
+          "uid": "-- Grafana --"
+        },
+        "enable": true,
+        "hide": true,
+        "iconColor": "rgba(0, 211, 255, 1)",
+        "name": "Annotations & Alerts",
+        "type": "dashboard"
+      }
+    ]
+  },
+  "editable": true,
+  "fiscalYearStartMonth": 0,
+  "graphTooltip": 0,
+  "id": null,
+  "links": [],
+  "liveNow": false,
+  "panels": [
+    {
+      "datasource": {
+        "type": "prometheus",
+        "uid": "prometheus"
+      },
+      "fieldConfig": {
+        "defaults": {
+          "unit": "reqps"
+        },
+        "overrides": []
+      },
+      "gridPos": {
+        "h": 8,
+        "w": 12,
+        "x": 0,
+        "y": 0
+      },
+      "id": 1,
+      "options": {
+        "legend": {
+          "calcs": [],
+          "displayMode": "list",
+          "placement": "bottom",
+          "showLegend": true
+        },
+        "tooltip": {
+          "mode": "single",
+          "sort": "none"
+        }
+      },
+      "targets": [
+        {
+          "datasource": {
+            "type": "prometheus",
+            "uid": "prometheus"
+          },
+          "editorMode": "code",
+          "expr": "sum by (endpoint) (rate(http_requests_total[5m]))",
+          "legendFormat": "{{endpoint}}",
+          "range": true,
+          "refId": "A"
+        }
+      ],
+      "title": "Request Rate by Endpoint",
+      "type": "timeseries"
+    },
+    {
+      "datasource": {
+        "type": "prometheus",
+        "uid": "prometheus"
+      },
+      "fieldConfig": {
+        "defaults": {
+          "unit": "reqps"
+        },
+        "overrides": []
+      },
+      "gridPos": {
+        "h": 8,
+        "w": 12,
+        "x": 12,
+        "y": 0
+      },
+      "id": 2,
+      "options": {
+        "legend": {
+          "calcs": [],
+          "displayMode": "list",
+          "placement": "bottom",
+          "showLegend": true
+        },
+        "tooltip": {
+          "mode": "single",
+          "sort": "none"
+        }
+      },
+      "targets": [
+        {
+          "datasource": {
+            "type": "prometheus",
+            "uid": "prometheus"
+          },
+          "editorMode": "code",
+          "expr": "sum(rate(http_requests_total{status_code=~\"5..\"}[5m]))",
+          "legendFormat": "5xx",
+          "range": true,
+          "refId": "A"
+        }
+      ],
+      "title": "Error Rate (5xx)",
+      "type": "timeseries"
+    },
+    {
+      "datasource": {
+        "type": "prometheus",
+        "uid": "prometheus"
+      },
+      "fieldConfig": {
+        "defaults": {
+          "unit": "s"
+        },
+        "overrides": []
+      },
+      "gridPos": {
+        "h": 8,
+        "w": 12,
+        "x": 0,
+        "y": 8
+      },
+      "id": 3,
+      "options": {
+        "legend": {
+          "calcs": [],
+          "displayMode": "list",
+          "placement": "bottom",
+          "showLegend": false
+        },
+        "tooltip": {
+          "mode": "single",
+          "sort": "none"
+        }
+      },
+      "targets": [
+        {
+          "datasource": {
+            "type": "prometheus",
+            "uid": "prometheus"
+          },
+          "editorMode": "code",
+          "expr": "histogram_quantile(0.95, sum by (le) (rate(http_request_duration_seconds_bucket[5m])))",
+          "legendFormat": "p95",
+          "range": true,
+          "refId": "A"
+        }
+      ],
+      "title": "Request Duration p95",
+      "type": "timeseries"
+    },
+    {
+      "datasource": {
+        "type": "prometheus",
+        "uid": "prometheus"
+      },
+      "fieldConfig": {
+        "defaults": {
+          "unit": "reqps"
+        },
+        "overrides": []
+      },
+      "gridPos": {
+        "h": 8,
+        "w": 12,
+        "x": 12,
+        "y": 8
+      },
+      "id": 4,
+      "options": {
+        "calculate": false,
+        "cellGap": 1,
+        "color": {
+          "mode": "scheme"
+        },
+        "exemplars": {
+          "color": "rgba(255,0,255,0.7)"
+        },
+        "filterValues": {
+          "le": 1e-9
+        },
+        "legend": {
+          "show": false
+        },
+        "rowsFrame": {
+          "layout": "auto"
+        },
+        "showValue": "never",
+        "tooltip": {
+          "show": true,
+          "yHistogram": false
+        },
+        "yAxis": {
+          "axisPlacement": "left",
+          "reverse": false,
+          "unit": "short"
+        }
+      },
+      "targets": [
+        {
+          "datasource": {
+            "type": "prometheus",
+            "uid": "prometheus"
+          },
+          "editorMode": "code",
+          "expr": "sum by (le) (rate(http_request_duration_seconds_bucket[5m]))",
+          "format": "heatmap",
+          "legendFormat": "{{le}}",
+          "range": true,
+          "refId": "A"
+        }
+      ],
+      "title": "Request Duration Heatmap",
+      "type": "heatmap"
+    },
+    {
+      "datasource": {
+        "type": "prometheus",
+        "uid": "prometheus"
+      },
+      "fieldConfig": {
+        "defaults": {
+          "min": 0,
+          "thresholds": {
+            "mode": "absolute",
+            "steps": [
+              {
+                "color": "green",
+                "value": null
+              },
+              {
+                "color": "orange",
+                "value": 5
+              },
+              {
+                "color": "red",
+                "value": 20
+              }
+            ]
+          },
+          "unit": "none"
+        },
+        "overrides": []
+      },
+      "gridPos": {
+        "h": 8,
+        "w": 8,
+        "x": 0,
+        "y": 16
+      },
+      "id": 5,
+      "options": {
+        "orientation": "auto",
+        "reduceOptions": {
+          "calcs": [
+            "lastNotNull"
+          ],
+          "fields": "",
+          "values": false
+        },
+        "showThresholdLabels": false,
+        "showThresholdMarkers": true
+      },
+      "targets": [
+        {
+          "datasource": {
+            "type": "prometheus",
+            "uid": "prometheus"
+          },
+          "editorMode": "code",
+          "expr": "sum(http_requests_in_progress)",
+          "refId": "A"
+        }
+      ],
+      "title": "Active Requests",
+      "type": "gauge"
+    },
+    {
+      "datasource": {
+        "type": "prometheus",
+        "uid": "prometheus"
+      },
+      "fieldConfig": {
+        "defaults": {},
+        "overrides": []
+      },
+      "gridPos": {
+        "h": 8,
+        "w": 8,
+        "x": 8,
+        "y": 16
+      },
+      "id": 6,
+      "options": {
+        "displayLabels": [
+          "name",
+          "percent"
+        ],
+        "legend": {
+          "displayMode": "list",
+          "placement": "right",
+          "showLegend": true
+        },
+        "pieType": "pie",
+        "reduceOptions": {
+          "calcs": [
+            "lastNotNull"
+          ],
+          "fields": "",
+          "values": false
+        }
+      },
+      "targets": [
+        {
+          "datasource": {
+            "type": "prometheus",
+            "uid": "prometheus"
+          },
+          "editorMode": "code",
+          "expr": "sum by (status_code) (rate(http_requests_total[5m]))",
+          "legendFormat": "{{status_code}}",
+          "refId": "A"
+        }
+      ],
+      "title": "Status Code Distribution",
+      "type": "piechart"
+    },
+    {
+      "datasource": {
+        "type": "prometheus",
+        "uid": "prometheus"
+      },
+      "fieldConfig": {
+        "defaults": {
+          "mappings": [
+            {
+              "options": {
+                "0": {
+                  "color": "red",
+                  "index": 0,
+                  "text": "DOWN"
+                },
+                "1": {
+                  "color": "green",
+                  "index": 1,
+                  "text": "UP"
+                }
+              },
+              "type": "value"
+            }
+          ],
+          "thresholds": {
+            "mode": "absolute",
+            "steps": [
+              {
+                "color": "red",
+                "value": null
+              },
+              {
+                "color": "green",
+                "value": 1
+              }
+            ]
+          }
+        },
+        "overrides": []
+      },
+      "gridPos": {
+        "h": 8,
+        "w": 8,
+        "x": 16,
+        "y": 16
+      },
+      "id": 7,
+      "options": {
+        "colorMode": "background",
+        "graphMode": "none",
+        "justifyMode": "center",
+        "orientation": "auto",
+        "reduceOptions": {
+          "calcs": [
+            "lastNotNull"
+          ],
+          "fields": "",
+          "values": false
+        },
+        "textMode": "value_and_name"
+      },
+      "targets": [
+        {
+          "datasource": {
+            "type": "prometheus",
+            "uid": "prometheus"
+          },
+          "editorMode": "code",
+          "expr": "up{job=\"app\"}",
+          "refId": "A"
+        }
+      ],
+      "title": "App Uptime",
+      "type": "stat"
+    }
+  ],
+  "refresh": "10s",
+  "schemaVersion": 40,
+  "style": "dark",
+  "tags": [
+    "lab8",
+    "prometheus",
+    "red"
+  ],
+  "templating": {
+    "list": []
+  },
+  "time": {
+    "from": "now-30m",
+    "to": "now"
+  },
+  "timepicker": {},
+  "timezone": "",
+  "title": "Lab 8 - Application Metrics",
+  "uid": "lab8-app-metrics",
+  "version": 1,
+  "weekStart": ""
+}
diff --git a/ansible/roles/monitoring/files/grafana-logs-dashboard.json b/ansible/roles/monitoring/files/grafana-logs-dashboard.json
new file mode 100644
index 0000000000..1411712d22
--- /dev/null
+++ b/ansible/roles/monitoring/files/grafana-logs-dashboard.json
@@ -0,0 +1,78 @@
+{
+  "annotations": {
+    "list": [
+      {
+        "builtIn": 1,
+        "datasource": {
+          "type": "grafana",
+          "uid": "-- Grafana --"
+        },
+        "enable": true,
+        "hide": true,
+        "iconColor": "rgba(0, 211, 255, 1)",
+        "name": "Annotations & Alerts",
+        "type": "dashboard"
+      }
+    ]
+  },
+  "editable": true,
+  "fiscalYearStartMonth": 0,
+  "graphTooltip": 0,
+  "id": null,
+  "links": [],
+  "panels": [
+    {
+      "datasource": {
+        "type": "loki",
+        "uid": "loki"
+      },
+      "gridPos": {
+        "h": 16,
+        "w": 24,
+        "x": 0,
+        "y": 0
+      },
+      "id": 1,
+      "options": {
+        "dedupStrategy": "none",
+        "enableLogDetails": true,
+        "prettifyLogMessage": false,
+        "showCommonLabels": false,
+        "showLabels": true,
+        "showTime": true,
+        "sortOrder": "Descending",
+        "wrapLogMessage": true
+      },
+      "targets": [
+        {
+          "datasource": {
+            "type": "loki",
+            "uid": "loki"
+          },
+          "editorMode": "code",
+          "expr": "{job=\"docker\"}",
+          "queryType": "range",
+          "refId": "A"
+        }
+      ],
+      "title": "Container Logs",
+      "type": "logs"
+    }
+  ],
+  "refresh": "10s",
+  "schemaVersion": 40,
+  "tags": [
+    "lab7",
+    "loki"
+  ],
+  "templating": {
+    "list": []
+  },
+  "time": {
+    "from": "now-1h",
+    "to": "now"
+  },
+  "title": "Lab 7 - Logs Overview",
+  "uid": "lab7-logs-overview",
+  "version": 1
+}
diff --git a/ansible/roles/monitoring/tasks/main.yml b/ansible/roles/monitoring/tasks/main.yml
index 8045115f61..bce6683c4b 100644
--- a/ansible/roles/monitoring/tasks/main.yml
+++ b/ansible/roles/monitoring/tasks/main.yml
@@ -1,5 +1,5 @@
 ---
-- name: Deploy Loki monitoring stack
+- name: Deploy observability stack
   tags:
     - monitoring_deploy
   block:
@@ -10,11 +10,14 @@
         mode: "0755"
       loop:
         - "{{ monitoring_project_dir }}"
+        - "{{ monitoring_project_dir }}/prometheus"
         - "{{ monitoring_project_dir }}/loki"
         - "{{ monitoring_project_dir }}/promtail"
         - "{{ monitoring_project_dir }}/grafana"
         - "{{ monitoring_project_dir }}/grafana/provisioning"
         - "{{ monitoring_project_dir }}/grafana/provisioning/datasources"
+        - "{{ monitoring_project_dir }}/grafana/provisioning/dashboards"
+        - "{{ monitoring_project_dir }}/grafana/provisioning/dashboards/json"
 
     - name: Render Loki configuration
       ansible.builtin.template:
@@ -28,11 +31,39 @@
         dest: "{{ monitoring_project_dir }}/promtail/config.yml"
         mode: "0644"
 
+    - name: Render Prometheus configuration
+      ansible.builtin.template:
+        src: prometheus.yml.j2
+        dest: "{{ monitoring_project_dir }}/prometheus/prometheus.yml"
+        mode: "0644"
+
     - name: Render Grafana datasource provisioning
       ansible.builtin.template:
         src: grafana-datasource.yml.j2
-        dest: "{{ monitoring_project_dir }}/grafana/provisioning/datasources/loki.yml"
+        dest: "{{ monitoring_project_dir }}/grafana/provisioning/datasources/datasources.yml"
+        mode: "0644"
+
+    - name: Remove legacy Loki-only datasource file
+      ansible.builtin.file:
+        path: "{{ monitoring_project_dir }}/grafana/provisioning/datasources/loki.yml"
+        state: absent
+
+    - name: Render Grafana dashboard provider
+      ansible.builtin.template:
+        src: grafana-dashboard-provider.yml.j2
+        dest: "{{ monitoring_project_dir }}/grafana/provisioning/dashboards/dashboards.yml"
+        mode: "0644"
+
+    - name: Provision Grafana dashboards
+      ansible.builtin.copy:
+        src: "{{ item.src }}"
+        dest: "{{ monitoring_project_dir }}/grafana/provisioning/dashboards/json/{{ item.dest }}"
         mode: "0644"
+      loop:
+        - src: grafana-app-dashboard.json
+          dest: app-metrics-dashboard.json
+        - src: grafana-logs-dashboard.json
+          dest: logs-dashboard.json
 
     - name: Render monitoring docker-compose file
       ansible.builtin.template:
@@ -61,6 +92,16 @@
       delay: 5
       until: monitoring_loki_ready.status == 200
 
+    - name: Wait for Prometheus health endpoint
+      ansible.builtin.uri:
+        url: "http://127.0.0.1:{{ prometheus_port }}/-/healthy"
+        status_code: 200
+        timeout: 10
+      register: monitoring_prometheus_health
+      retries: 12
+      delay: 5
+      until: monitoring_prometheus_health.status == 200
+
     - name: Wait for Grafana health endpoint
       ansible.builtin.uri:
         url: "http://127.0.0.1:{{ monitoring_grafana_port }}/api/health"
@@ -71,6 +112,16 @@
       delay: 5
       until: monitoring_grafana_health.status == 200
 
+    - name: Verify application health endpoint
+      ansible.builtin.uri:
+        url: "http://127.0.0.1:{{ monitoring_app_port }}/health"
+        status_code: 200
+        timeout: 10
+      register: monitoring_app_health
+      retries: 12
+      delay: 5
+      until: monitoring_app_health.status == 200
+
   rescue:
     - name: Show monitoring deployment diagnostics
       ansible.builtin.debug:
diff --git a/ansible/roles/monitoring/templates/docker-compose.yml.j2 b/ansible/roles/monitoring/templates/docker-compose.yml.j2
index 1edc2d13fe..ab3861a199 100644
--- a/ansible/roles/monitoring/templates/docker-compose.yml.j2
+++ b/ansible/roles/monitoring/templates/docker-compose.yml.j2
@@ -1,28 +1,61 @@
 name: {{ monitoring_compose_project_name }}
 
 services:
+  app-python:
+    image: "{{ monitoring_app_image }}:{{ monitoring_app_tag }}"
+    container_name: app-python
+    environment:
+      HOST: "0.0.0.0"
+      PORT: "{{ monitoring_app_internal_port }}"
+      DEBUG: "False"
+    ports:
+      - "{{ monitoring_app_port }}:{{ monitoring_app_internal_port }}"
+    networks:
+      - logging
+    labels:
+      logging: "promtail"
+      app: "devops-info-service"
+    healthcheck:
+      test: ["CMD-SHELL", "python -c \"import urllib.request; urllib.request.urlopen('http://localhost:{{ monitoring_app_internal_port }}/health')\""]
+      interval: 10s
+      timeout: 5s
+      retries: 5
+    deploy:
+      resources:
+        limits:
+          memory: 256M
+          cpus: "0.5"
+    restart: unless-stopped
+
   loki:
     image: {{ monitoring_loki_image }}
-    container_name: devops-loki
+    container_name: loki
     command: -config.file=/etc/loki/config.yml
     ports:
       - "{{ monitoring_loki_port }}:{{ monitoring_loki_port }}"
     volumes:
       - ./loki/config.yml:/etc/loki/config.yml:ro
       - loki-data:/loki
+    networks:
+      - logging
     labels:
       logging: "promtail"
-      app: "devops-loki"
+      app: "loki"
     healthcheck:
       test: ["CMD-SHELL", "wget -qO- http://localhost:{{ monitoring_loki_port }}/ready >/dev/null 2>&1 || curl -fsS http://localhost:{{ monitoring_loki_port }}/ready >/dev/null 2>&1"]
-      interval: 15s
+      interval: 10s
       timeout: 5s
-      retries: 10
-      start_period: 20s
+      retries: 5
+    deploy:
+      resources:
+        limits:
+          memory: 1G
+          cpus: "1.0"
+    restart: unless-stopped
 
   promtail:
     image: {{ monitoring_promtail_image }}
-    container_name: devops-promtail
+    container_name: promtail
     command: -config.file=/etc/promtail/config.yml
     ports:
       - "{{ monitoring_promtail_port }}:{{ monitoring_promtail_port }}"
@@ -32,36 +65,92 @@ services:
     depends_on:
       loki:
         condition: service_healthy
+    networks:
+      - logging
+    labels:
+      logging: "promtail"
+      app: "promtail"
+    healthcheck:
+      test: ["CMD-SHELL", "grep -qi ':{{ '%x' % (monitoring_promtail_port | int) }}' /proc/net/tcp /proc/net/tcp6"]
+      interval: 10s
+      timeout: 5s
+      retries: 5
+    deploy:
+      resources:
+        limits:
+          memory: 256M
+          cpus: "0.5"
+    restart: unless-stopped
+
+  prometheus:
+    image: "prom/prometheus:v{{ prometheus_version }}"
+    container_name: prometheus
+    command:
+      - "--config.file=/etc/prometheus/prometheus.yml"
+      - "--storage.tsdb.retention.time={{ prometheus_retention_days }}d"
+      - "--storage.tsdb.retention.size={{ prometheus_retention_size }}"
+    ports:
+      - "{{ prometheus_port }}:{{ prometheus_port }}"
+    volumes:
+      - ./prometheus/prometheus.yml:/etc/prometheus/prometheus.yml:ro
+      - prometheus-data:/prometheus
+    networks:
+      - logging
     labels:
       logging: "promtail"
-      app: "devops-promtail"
+      app: "prometheus"
+    healthcheck:
+      test: ["CMD-SHELL", "wget --no-verbose --tries=1 --spider http://localhost:{{ prometheus_port }}/-/healthy || exit 1"]
+      interval: 10s
+      timeout: 5s
+      retries: 5
+    deploy:
+      resources:
+        limits:
+          memory: 1G
+          cpus: "1.0"
+    restart: unless-stopped
 
   grafana:
     image: {{ monitoring_grafana_image }}
-    container_name: devops-grafana
+    container_name: grafana
     ports:
       - "{{ monitoring_grafana_port }}:{{ monitoring_grafana_port }}"
     environment:
-      GF_AUTH_ANONYMOUS_ENABLED: "false"
       GF_SECURITY_ADMIN_USER: "{{ monitoring_grafana_admin_user }}"
       GF_SECURITY_ADMIN_PASSWORD: "{{ monitoring_grafana_admin_password }}"
       GF_USERS_ALLOW_SIGN_UP: "false"
+      GF_METRICS_ENABLED: "true"
     volumes:
       - grafana-data:/var/lib/grafana
       - ./grafana/provisioning:/etc/grafana/provisioning:ro
     depends_on:
       loki:
         condition: service_healthy
+      prometheus:
+        condition: service_healthy
+    networks:
+      - logging
     labels:
       logging: "promtail"
-      app: "devops-grafana"
+      app: "grafana"
     healthcheck:
       test: ["CMD-SHELL", "wget -qO- http://localhost:{{ monitoring_grafana_port }}/api/health >/dev/null 2>&1 || curl -fsS http://localhost:{{ monitoring_grafana_port }}/api/health >/dev/null 2>&1"]
-      interval: 15s
+      interval: 10s
       timeout: 5s
-      retries: 10
-      start_period: 30s
+      retries: 5
+    deploy:
+      resources:
+        limits:
+          memory: 512M
+          cpus: "0.5"
+    restart: unless-stopped
 
 volumes:
   loki-data:
   grafana-data:
+  prometheus-data:
+
+networks:
+  logging:
+    driver: bridge
diff --git a/ansible/roles/monitoring/templates/grafana-dashboard-provider.yml.j2 b/ansible/roles/monitoring/templates/grafana-dashboard-provider.yml.j2
new file mode 100644
index 0000000000..52ce418c92
--- /dev/null
+++ b/ansible/roles/monitoring/templates/grafana-dashboard-provider.yml.j2
@@ -0,0 +1,11 @@
+apiVersion: 1
+
+providers:
+  - name: 'default'
+    orgId: 1
+    folder: 'Lab 8'
+    type: file
+    disableDeletion: false
+    editable: true
+    options:
+      path: /etc/grafana/provisioning/dashboards/json
diff --git a/ansible/roles/monitoring/templates/grafana-datasource.yml.j2 b/ansible/roles/monitoring/templates/grafana-datasource.yml.j2
index f13a7c7c40..c924e3d9cf 100644
--- a/ansible/roles/monitoring/templates/grafana-datasource.yml.j2
+++ b/ansible/roles/monitoring/templates/grafana-datasource.yml.j2
@@ -1,10 +1,16 @@
 apiVersion: 1
 
 datasources:
+  - name: Prometheus
+    uid: prometheus
+    type: prometheus
+    access: proxy
+    url: http://prometheus:{{ prometheus_port }}
+    editable: true
+
   - name: Loki
     uid: loki
     type: loki
     access: proxy
     url: http://loki:{{ monitoring_loki_port }}
-    isDefault: true
     editable: true
diff --git a/ansible/roles/monitoring/templates/prometheus.yml.j2 b/ansible/roles/monitoring/templates/prometheus.yml.j2
new file mode 100644
index 0000000000..8a4e49654a
--- /dev/null
+++ b/ansible/roles/monitoring/templates/prometheus.yml.j2
@@ -0,0 +1,16 @@
+global:
+  scrape_interval: {{ prometheus_scrape_interval }}
+  evaluation_interval: {{ prometheus_scrape_interval }}
+
+scrape_configs:
+{% for target in prometheus_targets %}
+  - job_name: '{{ target.job }}'
+    static_configs:
+      - targets:
+{% for endpoint in target.targets %}
+          - '{{ endpoint }}'
+{% endfor %}
+{% if target.path is defined %}
+    metrics_path: '{{ target.path }}'
+{% endif %}
+{% endfor %}
diff --git a/ansible/roles/monitoring/templates/promtail-config.yml.j2 b/ansible/roles/monitoring/templates/promtail-config.yml.j2
index f7c374f3ba..76edcd9103 100644
--- a/ansible/roles/monitoring/templates/promtail-config.yml.j2
+++ b/ansible/roles/monitoring/templates/promtail-config.yml.j2
@@ -16,6 +16,9 @@ scrape_configs:
     pipeline_stages:
       - docker: {}
     relabel_configs:
+      - source_labels: ["__meta_docker_container_label_logging"]
+        regex: promtail
+        action: keep
       - source_labels: ["__meta_docker_container_name"]
         regex: "/(.*)"
         target_label: container
diff --git a/app_python/README.md b/app_python/README.md
index 58894af2b1..5678c7a3a4 100644
--- a/app_python/README.md
+++ b/app_python/README.md
@@ -42,6 +42,15 @@ HOST=127.0.0.1 PORT=3000 DEBUG=true python app.py
 - `GET /health` – Health check
   - Returns basic health status, timestamp, and uptime in seconds
 
+- `GET /metrics` – Prometheus metrics endpoint
+  - Exposes RED metrics:
+    - `http_requests_total{method,endpoint,status_code}`
+    - `http_request_duration_seconds{method,endpoint,status_code}`
+    - `http_requests_in_progress{method,endpoint}`
+  - Exposes app-specific metrics:
+    - `devops_info_endpoint_calls{endpoint}`
+    - `devops_info_system_collection_seconds`
+
 ## Configuration
 
 Configuration is done via environment variables:
diff --git a/app_python/app.py b/app_python/app.py
index c3712632ec..57cb8ece4c 100644
--- a/app_python/app.py
+++ b/app_python/app.py
@@ -12,7 +12,8 @@
 from datetime import datetime, timezone
 from typing import Any, Dict
 
-from flask import Flask, g, jsonify, request
+from flask import Flask, Response, g, jsonify, request
+from prometheus_client import CONTENT_TYPE_LATEST, Counter, Gauge, Histogram, generate_latest
 
 
 app = Flask(__name__)
@@ -76,6 +77,32 @@ def configure_logging() -> logging.Logger:
     },
 )
 
+# Prometheus metrics (RED method + app-specific signals)
+HTTP_REQUESTS_TOTAL = Counter(
+    "http_requests_total",
+    "Total HTTP requests",
+    ["method", "endpoint", "status_code"],
+)
+HTTP_REQUEST_DURATION_SECONDS = Histogram(
+    "http_request_duration_seconds",
+    "HTTP request duration in seconds",
+    ["method", "endpoint", "status_code"],
+)
+HTTP_REQUESTS_IN_PROGRESS = Gauge(
+    "http_requests_in_progress",
+    "HTTP requests currently being processed",
+    ["method", "endpoint"],
+)
+DEVOPS_INFO_ENDPOINT_CALLS = Counter(
+    "devops_info_endpoint_calls",
+    "Total endpoint calls in DevOps info service",
+    ["endpoint"],
+)
+DEVOPS_INFO_SYSTEM_COLLECTION_SECONDS = Histogram(
+    "devops_info_system_collection_seconds",
+    "System information collection duration in seconds",
+)
+
 
 def get_uptime() -> Dict[str, Any]:
     """Return uptime in seconds and human-readable form."""
@@ -91,14 +118,18 @@ def get_uptime() -> Dict[str, Any]:
 
 def get_system_info() -> Dict[str, Any]:
     """Collect system information."""
-    return {
-        "hostname": socket.gethostname(),
-        "platform": platform.system(),
-        "platform_version": platform.platform(),
-        "architecture": platform.machine(),
-        "cpu_count": os.cpu_count() or 1,
-        "python_version": platform.python_version(),
-    }
+    started_at = time.perf_counter()
+    try:
+        return {
+            "hostname": socket.gethostname(),
+            "platform": platform.system(),
+            "platform_version": platform.platform(),
+            "architecture": platform.machine(),
+            "cpu_count": os.cpu_count() or 1,
+            "python_version": platform.python_version(),
+        }
+    finally:
+        DEVOPS_INFO_SYSTEM_COLLECTION_SECONDS.observe(time.perf_counter() - started_at)
 
 
 def get_request_info() -> Dict[str, Any]:
@@ -114,21 +145,48 @@ def get_request_info() -> Dict[str, Any]:
     }
 
 
+def get_normalized_endpoint() -> str:
+    """Map routes to low-cardinality labels for Prometheus metrics."""
+    if request.url_rule is not None and request.url_rule.rule:
+        return request.url_rule.rule
+    if request.path in {"/", "/health", "/metrics"}:
+        return request.path
+    return "/unknown"
+
+
 @app.before_request
 def before_request_logging() -> None:
-    """Track request start time for latency logging."""
+    """Track request start for logging and metrics."""
     g.request_started_at = time.perf_counter()
+    g.request_endpoint = get_normalized_endpoint()
+    HTTP_REQUESTS_IN_PROGRESS.labels(
+        method=request.method, endpoint=g.request_endpoint
+    ).inc()
 
 
 @app.after_request
 def after_request_logging(response):
-    """Emit one structured log entry per HTTP request."""
+    """Emit logs and collect request metrics."""
     request_info = get_request_info()
     request_info["status_code"] = response.status_code
 
+    endpoint = getattr(g, "request_endpoint", get_normalized_endpoint())
+    method = request.method
+    status_code = str(response.status_code)
+
     started_at = getattr(g, "request_started_at", None)
+    duration_seconds = 0.0
     if started_at is not None:
-        request_info["duration_ms"] = round((time.perf_counter() - started_at) * 1000, 2)
+        duration_seconds = time.perf_counter() - started_at
+        request_info["duration_ms"] = round(duration_seconds * 1000, 2)
+
+    HTTP_REQUESTS_TOTAL.labels(
+        method=method, endpoint=endpoint, status_code=status_code
+    ).inc()
+    HTTP_REQUEST_DURATION_SECONDS.labels(
+        method=method, endpoint=endpoint, status_code=status_code
+    ).observe(duration_seconds)
+    HTTP_REQUESTS_IN_PROGRESS.labels(method=method, endpoint=endpoint).dec()
 
     logger.info("HTTP request handled", extra={"context": request_info})
     return response
@@ -137,6 +195,7 @@ def after_request_logging(response):
 @app.route("/", methods=["GET"])
 def index():
     """Main endpoint - service and system information."""
+    DEVOPS_INFO_ENDPOINT_CALLS.labels(endpoint="/").inc()
     uptime = get_uptime()
     system_info = get_system_info()
     request_info = get_request_info()
@@ -167,6 +226,11 @@ def index():
                 "method": "GET",
                 "description": "Health check",
             },
+            {
+                "path": "/metrics",
+                "method": "GET",
+                "description": "Prometheus metrics",
+            },
         ],
     }
 
@@ -176,6 +240,7 @@ def index():
 @app.route("/health", methods=["GET"])
 def health():
     """Health check endpoint."""
+    DEVOPS_INFO_ENDPOINT_CALLS.labels(endpoint="/health").inc()
     uptime = get_uptime()
     payload = {
         "status": "healthy",
@@ -185,6 +250,13 @@ def health():
     return jsonify(payload), 200
 
 
+@app.route("/metrics", methods=["GET"])
+def metrics():
+    """Expose Prometheus scrape endpoint."""
+    DEVOPS_INFO_ENDPOINT_CALLS.labels(endpoint="/metrics").inc()
+    return Response(generate_latest(), mimetype=CONTENT_TYPE_LATEST)
+
+
 @app.errorhandler(404)
 def not_found(error):
     """Return JSON for 404 errors."""
diff --git a/app_python/requirements.txt b/app_python/requirements.txt
index 22ac75b399..46c776bf8d 100644
--- a/app_python/requirements.txt
+++ b/app_python/requirements.txt
@@ -1 +1,2 @@
 Flask==3.1.0
+prometheus-client==0.23.1
diff --git a/app_python/tests/test_app.py b/app_python/tests/test_app.py
index 222f4ab610..4179b4fda0 100644
--- a/app_python/tests/test_app.py
+++ b/app_python/tests/test_app.py
@@ -80,7 +80,22 @@ def test_not_found_returns_json_404(self):
         self.assertEqual(data["error"], "Not Found")
         self.assertIn("message", data)
 
+    def test_metrics_endpoint_exposes_prometheus_metrics(self):
+        # Generate a few requests so metrics have data points.
+        self.client.get("/")
+        self.client.get("/health")
+
+        resp = self.client.get("/metrics")
+        self.assertEqual(resp.status_code, 200)
+
+        body = resp.get_data(as_text=True)
+        self.assertIn("# HELP http_requests_total", body)
+        self.assertIn("# TYPE http_requests_total counter", body)
+        self.assertIn("http_request_duration_seconds", body)
+        self.assertIn("http_requests_in_progress", body)
+        self.assertIn("devops_info_endpoint_calls_total", body)
+        self.assertIn("devops_info_system_collection_seconds", body)
+
 
 if __name__ == "__main__":
     unittest.main()
-
diff --git a/monitoring/docker-compose.yml b/monitoring/docker-compose.yml
index 6dd75f6f2e..48a621f0a9 100644
--- a/monitoring/docker-compose.yml
+++ b/monitoring/docker-compose.yml
@@ -1,9 +1,56 @@
 name: devops-monitoring
 
 services:
+  app-python:
+    build:
+      context: ../app_python
+    container_name: app-python
+    environment:
+      HOST: 0.0.0.0
+      PORT: "8000"
+      DEBUG: "False"
+    ports:
+      - "8000:8000"
+    networks:
+      - logging
+    labels:
+      logging: "promtail"
+      app: "devops-info-service"
+    healthcheck:
+      test: ["CMD-SHELL", "python -c \"import urllib.request; urllib.request.urlopen('http://localhost:8000/health')\""]
+      interval: 10s
+      timeout: 5s
+      retries: 5
+    deploy:
+      resources:
+        limits:
+          memory: 256M
+          cpus: "0.5"
+    restart: unless-stopped
+
+  devops-go:
+    build:
+      context: ../app_go
+    container_name: devops-go
+    environment:
+      PORT: "8001"
+    ports:
+      - "8001:8001"
+    networks:
+      - logging
+    labels:
+      logging: "promtail"
+      app: "devops-go"
+    deploy:
+      resources:
+        limits:
+          memory: 256M
+          cpus: "0.5"
+    restart: unless-stopped
+
   loki:
     image: grafana/loki:3.0.0
-    container_name: devops-loki
+    container_name: loki
     command: -config.file=/etc/loki/config.yml
     ports:
       - "3100:3100"
@@ -14,148 +61,117 @@ services:
       - logging
     labels:
       logging: "promtail"
-      app: "devops-loki"
+      app: "loki"
     healthcheck:
       test: ["CMD-SHELL", "wget -qO- http://localhost:3100/ready >/dev/null 2>&1 || curl -fsS http://localhost:3100/ready >/dev/null 2>&1"]
-      interval: 15s
+      interval: 10s
       timeout: 5s
-      retries: 10
-      start_period: 20s
+      retries: 5
     deploy:
       resources:
         limits:
-          cpus: "1.0"
           memory: 1G
-        reservations:
-          cpus: "0.25"
-          memory: 256M
+          cpus: "1.0"
+    restart: unless-stopped
 
   promtail:
     image: grafana/promtail:3.0.0
-    container_name: devops-promtail
+    container_name: promtail
     command: -config.file=/etc/promtail/config.yml
     ports:
       - "9080:9080"
     volumes:
       - ./promtail/config.yml:/etc/promtail/config.yml:ro
       - /var/run/docker.sock:/var/run/docker.sock:ro
-    networks:
-      - logging
     depends_on:
       loki:
         condition: service_healthy
-    labels:
-      logging: "promtail"
-      app: "devops-promtail"
-    deploy:
-      resources:
-        limits:
-          cpus: "0.5"
-          memory: 512M
-        reservations:
-          cpus: "0.10"
-          memory: 128M
-
-  grafana:
-    image: grafana/grafana:12.3.1
-    container_name: devops-grafana
-    ports:
-      - "3000:3000"
-    environment:
-      GF_AUTH_ANONYMOUS_ENABLED: "false"
-      GF_SECURITY_ADMIN_USER: "${GRAFANA_ADMIN_USER:-admin}"
-      GF_SECURITY_ADMIN_PASSWORD: "${GRAFANA_ADMIN_PASSWORD:-change-me-in-dot-env}"
-      GF_USERS_ALLOW_SIGN_UP: "false"
-    volumes:
-      - grafana-data:/var/lib/grafana
-      - ./grafana/provisioning:/etc/grafana/provisioning:ro
     networks:
       - logging
-    depends_on:
-      loki:
-        condition: service_healthy
     labels:
       logging: "promtail"
-      app: "devops-grafana"
+      app: "promtail"
     healthcheck:
-      test: ["CMD-SHELL", "wget -qO- http://localhost:3000/api/health >/dev/null 2>&1 || curl -fsS http://localhost:3000/api/health >/dev/null 2>&1"]
-      interval: 15s
+      test: ["CMD-SHELL", "grep -qi ':2388' /proc/net/tcp /proc/net/tcp6"]
+      interval: 10s
       timeout: 5s
-      retries: 10
-      start_period: 30s
+      retries: 5
     deploy:
       resources:
         limits:
-          cpus: "1.0"
-          memory: 1G
-        reservations:
-          cpus: "0.25"
           memory: 256M
+          cpus: "0.5"
+    restart: unless-stopped
 
-  devops-python:
-    build:
-      context: ../app_python
-    image: devops-python:lab07
-    container_name: devops-python
+  prometheus:
+    image: prom/prometheus:v3.9.0
+    container_name: prometheus
+    command:
+      - '--config.file=/etc/prometheus/prometheus.yml'
+      - '--storage.tsdb.retention.time=15d'
+      - '--storage.tsdb.retention.size=10GB'
     ports:
-      - "8000:8000"
-    environment:
-      HOST: "0.0.0.0"
-      PORT: "8000"
-      DEBUG: "false"
+      - "9090:9090"
+    volumes:
+      - ./prometheus/prometheus.yml:/etc/prometheus/prometheus.yml:ro
+      - prometheus-data:/prometheus
     networks:
       - logging
     labels:
       logging: "promtail"
-      app: "devops-python"
+      app: "prometheus"
     healthcheck:
-      test: ["CMD-SHELL", "wget -qO- http://localhost:8000/health >/dev/null 2>&1 || curl -fsS http://localhost:8000/health >/dev/null 2>&1"]
-      interval: 15s
+      test: ["CMD-SHELL", "wget --no-verbose --tries=1 --spider http://localhost:9090/-/healthy || exit 1"]
+      interval: 10s
       timeout: 5s
-      retries: 10
-      start_period: 20s
+      retries: 5
     deploy:
       resources:
         limits:
-          cpus: "0.5"
-          memory: 512M
-        reservations:
-          cpus: "0.10"
-          memory: 128M
+          memory: 1G
+          cpus: "1.0"
+    restart: unless-stopped
 
-  devops-go:
-    build:
-      context: ../app_go
-    image: devops-go:lab07
-    container_name: devops-go
-    ports:
-      - "8001:8001"
+  grafana:
+    image: grafana/grafana:12.3.1
+    container_name: grafana
     environment:
-      PORT: "8001"
+      GF_SECURITY_ADMIN_USER: ${GRAFANA_ADMIN_USER:-admin}
+      GF_SECURITY_ADMIN_PASSWORD: ${GRAFANA_ADMIN_PASSWORD:-password}
+      GF_USERS_ALLOW_SIGN_UP: "false"
+      GF_METRICS_ENABLED: "true"
+    ports:
+      - "3000:3000"
+    volumes:
+      - grafana-data:/var/lib/grafana
+      - ./grafana/provisioning:/etc/grafana/provisioning:ro
+    depends_on:
+      loki:
+        condition: service_healthy
+      prometheus:
+        condition: service_healthy
     networks:
       - logging
     labels:
       logging: "promtail"
-      app: "devops-go"
+      app: "grafana"
     healthcheck:
-      test: ["CMD-SHELL", "wget -qO- http://localhost:8001/health >/dev/null 2>&1 || curl -fsS http://localhost:8001/health >/dev/null 2>&1"]
-      interval: 15s
+      test: ["CMD-SHELL", "wget -qO- http://localhost:3000/api/health >/dev/null 2>&1 || curl -fsS http://localhost:3000/api/health >/dev/null 2>&1"]
+      interval: 10s
       timeout: 5s
-      retries: 10
-      start_period: 20s
+      retries: 5
     deploy:
       resources:
         limits:
-          cpus: "0.5"
           memory: 512M
-        reservations:
-          cpus: "0.10"
-          memory: 128M
-
-networks:
-  logging:
-    driver: bridge
+          cpus: "0.5"
+    restart: unless-stopped
 
 volumes:
   loki-data:
   grafana-data:
+  prometheus-data:
+
+networks:
+  logging:
+    driver: bridge
diff --git a/monitoring/docs/LAB08.md b/monitoring/docs/LAB08.md
new file mode 100644
index 0000000000..bb11d73e12
--- /dev/null
+++ b/monitoring/docs/LAB08.md
@@ -0,0 +1,226 @@
+# LAB08 — Metrics & Monitoring with Prometheus
+
+## 1. Architecture
+
+### Monitoring flow
+
+```mermaid
+flowchart LR
+    APP[Python App\n/health, /metrics] -->|scrape 15s| PROM[Prometheus]
+    LOKI[Loki /metrics] -->|scrape 15s| PROM
+    GRAFANA[Grafana /metrics] -->|scrape 15s| PROM
+
+    APP -->|container logs| PROMTAIL[Promtail]
+    PROMTAIL -->|push logs| LOKI
+
+    PROM --> GRAFANA_UI[Grafana Dashboards]
+    LOKI --> GRAFANA_UI
+```
+
+### Components
+
+- `app-python`: Flask app instrumented with Prometheus metrics (RED + app-specific).
+- `devops-go`: optional second app from Lab 1 kept in stack for log collection compatibility.
+- `prometheus`: pulls metrics from app, Loki, Grafana, and itself every `15s`.
+- `grafana`: visualizes Prometheus and Loki data with provisioned dashboards.
+- `loki` + `promtail`: log aggregation pipeline from Lab 7.
+
+## 2. Application Instrumentation
+
+File: `app_python/app.py`
+
+### Implemented metrics
+
+- `http_requests_total{method,endpoint,status_code}` (Counter)
+  - Tracks total request count (Rate + Errors via status filtering).
+- `http_request_duration_seconds{method,endpoint,status_code}` (Histogram)
+  - Tracks response latency distribution (Duration).
+- `http_requests_in_progress{method,endpoint}` (Gauge)
+  - Tracks concurrent requests.
+- `devops_info_endpoint_calls{endpoint}` (Counter)
+  - App-specific endpoint usage metric.
+- `devops_info_system_collection_seconds` (Histogram)
+  - App-specific internal operation timing (system info collection).
+
+### Instrumentation points
+
+- `@app.before_request`
+  - Stores start time and increments in-progress gauge.
+- `@app.after_request`
+  - Records request counter + histogram and decrements in-progress gauge.
+- `@app.route("/metrics")`
+  - Exposes Prometheus text format using `generate_latest()`.
+
+### Label strategy
+
+- Low cardinality endpoint normalization:
+  - Known routes keep their route labels (`/`, `/health`, `/metrics`).
+  - Unknown paths are grouped into `/unknown`.
+- Avoid per-user or per-id labels.
+
+## 3. Prometheus Configuration
+
+File: `monitoring/prometheus/prometheus.yml`
+
+### Global settings
+
+- `scrape_interval: 15s`
+- `evaluation_interval: 15s`
+
+### Scrape targets
+
+- `prometheus`: `localhost:9090`
+- `app`: `app-python:8000` (`/metrics`)
+- `loki`: `loki:3100` (`/metrics`)
+- `grafana`: `grafana:3000` (`/metrics`)
+
+### Retention policy
+
+Configured in `monitoring/docker-compose.yml` Prometheus command flags:
+
+- `--storage.tsdb.retention.time=15d`
+- `--storage.tsdb.retention.size=10GB`
+
+## 4. Dashboard Walkthrough
+
+Provisioned dashboard JSON:
+
+- `monitoring/grafana/provisioning/dashboards/json/app-metrics-dashboard.json`
+
+### Panels (6+)
+
+1. **Request Rate by Endpoint**
+   - `sum by (endpoint) (rate(http_requests_total[5m]))`
+2. **Error Rate (5xx)**
+   - `sum(rate(http_requests_total{status_code=~"5.."}[5m]))`
+3. **Request Duration p95**
+   - `histogram_quantile(0.95, sum by (le) (rate(http_request_duration_seconds_bucket[5m])))`
+4. **Request Duration Heatmap**
+   - `sum by (le) (rate(http_request_duration_seconds_bucket[5m]))`
+5. **Active Requests**
+   - `sum(http_requests_in_progress)`
+6. **Status Code Distribution**
+   - `sum by (status_code) (rate(http_requests_total[5m]))`
+7. **App Uptime (UP/DOWN)**
+   - `up{job="app"}`
+
+## 5. PromQL Examples
+
+1. Requests per second by endpoint:
+   - `sum by (endpoint) (rate(http_requests_total[5m]))`
+2. Global request rate:
+   - `sum(rate(http_requests_total[5m]))`
+3. 5xx error rate:
+   - `sum(rate(http_requests_total{status_code=~"5.."}[5m]))`
+4. Error percentage:
+   - `100 * sum(rate(http_requests_total{status_code=~"5.."}[5m])) / sum(rate(http_requests_total[5m]))`
+5. p95 latency:
+   - `histogram_quantile(0.95, sum by (le) (rate(http_request_duration_seconds_bucket[5m])))`
+6. Active requests now:
+   - `sum(http_requests_in_progress)`
+7. Target availability:
+   - `up`
+
+## 6. Production Setup
+
+### Health checks
+
+Configured for all services in `monitoring/docker-compose.yml`:
+
+- `app-python`: `/health`
+- `prometheus`: `/-/healthy`
+- `grafana`: `/api/health`
+- `loki`: `/ready`
+- `promtail`: `/ready`
+
+### Resource limits
+
+- Prometheus: `1G`, `1.0 CPU`
+- Loki: `1G`, `1.0 CPU`
+- Grafana: `512M`, `0.5 CPU`
+- App: `256M`, `0.5 CPU`
+- Promtail: `256M`, `0.5 CPU`
+
+### Persistence
+
+Named volumes:
+
+- `prometheus-data`
+- `loki-data`
+- `grafana-data`
+
+Data and dashboards remain after `docker compose down` / `up -d`.
+
+## 7. Testing Results
+
+### Local validation commands
+
+```bash
+# App tests
+python -m unittest app_python/tests/test_app.py
+
+# Compose syntax
+cd monitoring
+docker compose config
+
+# Start stack
+docker compose up -d
+
+docker compose ps
+curl -s http://localhost:8000/metrics | head -40
+curl -s http://localhost:9090/api/v1/query?query=up
+```
+
+### Evidence to capture
+
+Store screenshots in `monitoring/docs/screenshots/` with names:
+
+- `metrics-endpoint.png` (browser/curl output of `/metrics`)
+- `prometheus-targets-up.png` (`http://localhost:9090/targets` all UP)
+- `promql-up-query.png` (`up` query result)
+- `grafana-app-dashboard1.png` (custom dashboard with 6+ panels)
+- `grafana-app-dashboard2.png` (custom dashboard with 6+ panels)
+- `compose-healthy.png` (`docker compose ps` healthy services)
+- `persistence-proof.png` (dashboard exists after restart)
+
+## 8. Challenges & Solutions
+
+- **High-cardinality risk for endpoint labels**
+  - Solution: normalized unknown paths to `/unknown`.
+- **Prometheus retention requirements**
+  - Solution: set explicit TSDB retention by time and size in container command.
+- **Repeatable dashboard setup**
+  - Solution: provisioning files + dashboard JSON committed to repo.
+- **Automation requirement (bonus)**
+  - Solution: extended Ansible `monitoring` role with templated Prometheus and dashboard provisioning.
+
+## Metrics vs Logs (Lab 7 vs Lab 8)
+
+- Use **metrics** for trends/SLOs/alerts (rate, error rate, p95, uptime).
+- Use **logs** for event-level debugging and root-cause analysis.
+- Together they cover both macro health (metrics) and request-level detail (logs).
+
+## Bonus — Ansible Automation
+
+Extended role: `ansible/roles/monitoring`
+
+### Implemented
+
+- Added Prometheus variables and scrape target list in `defaults/main.yml`.
+- Added Jinja2 Prometheus template: `templates/prometheus.yml.j2`.
+- Updated Compose template to include:
+  - app + Loki + Promtail + Prometheus + Grafana
+  - health checks, resource limits, retention, persistent volumes.
+- Provisioned Grafana data sources (Loki + Prometheus) and dashboards.
+- Added dashboard files:
+  - `files/grafana-app-dashboard.json`
+  - `files/grafana-logs-dashboard.json`
+
+### End-to-end deployment
+
+```bash
+cd ansible
+ansible-playbook playbooks/deploy-monitoring.yml -i inventory/hosts.ini --ask-vault-pass
+```
+
+Run twice to verify idempotency (`changed=0` expected on second run for stable state).
diff --git a/monitoring/docs/screenshots/ promql-up-query.png b/monitoring/docs/screenshots/ promql-up-query.png
new file mode 100644
index 0000000000..095a7bf573
Binary files /dev/null and b/monitoring/docs/screenshots/ promql-up-query.png differ
diff --git a/monitoring/docs/screenshots/afteerrestart.png b/monitoring/docs/screenshots/afteerrestart.png
new file mode 100644
index 0000000000..18a6cd0924
Binary files /dev/null and b/monitoring/docs/screenshots/afteerrestart.png differ
diff --git a/monitoring/docs/screenshots/compose-healthyyyy.png b/monitoring/docs/screenshots/compose-healthyyyy.png
new file mode 100644
index 0000000000..cfdd5c3434
Binary files /dev/null and b/monitoring/docs/screenshots/compose-healthyyyy.png differ
diff --git a/monitoring/docs/screenshots/grafana-app-dashboard1.png b/monitoring/docs/screenshots/grafana-app-dashboard1.png
new file mode 100644
index 0000000000..837b5fc57d
Binary files /dev/null and b/monitoring/docs/screenshots/grafana-app-dashboard1.png differ
diff --git a/monitoring/docs/screenshots/grafana-app-dashboard2.png b/monitoring/docs/screenshots/grafana-app-dashboard2.png
new file mode 100644
index 0000000000..2ee706acad
Binary files /dev/null and b/monitoring/docs/screenshots/grafana-app-dashboard2.png differ
diff --git a/monitoring/docs/screenshots/metrics-endpoint.png b/monitoring/docs/screenshots/metrics-endpoint.png
new file mode 100644
index 0000000000..9eb2fbaa82
Binary files /dev/null and b/monitoring/docs/screenshots/metrics-endpoint.png differ
diff --git a/monitoring/docs/screenshots/persistence-proof.png b/monitoring/docs/screenshots/persistence-proof.png
new file mode 100644
index 0000000000..da847273d8
Binary files /dev/null and b/monitoring/docs/screenshots/persistence-proof.png differ
diff --git a/monitoring/docs/screenshots/prometheus-targets-up.png b/monitoring/docs/screenshots/prometheus-targets-up.png
new file mode 100644
index 0000000000..3bc935c37d
Binary files /dev/null and b/monitoring/docs/screenshots/prometheus-targets-up.png differ
diff --git a/monitoring/grafana/provisioning/dashboards/dashboards.yml b/monitoring/grafana/provisioning/dashboards/dashboards.yml
new file mode 100644
index 0000000000..52ce418c92
--- /dev/null
+++ b/monitoring/grafana/provisioning/dashboards/dashboards.yml
@@ -0,0 +1,11 @@
+apiVersion: 1
+
+providers:
+  - name: 'default'
+    orgId: 1
+    folder: 'Lab 8'
+    type: file
+    disableDeletion: false
+    editable: true
+    options:
+      path: /etc/grafana/provisioning/dashboards/json
diff --git a/monitoring/grafana/provisioning/dashboards/json/app-metrics-dashboard.json b/monitoring/grafana/provisioning/dashboards/json/app-metrics-dashboard.json
new file mode 100644
index 0000000000..2f4ceb99c8
--- /dev/null
+++ b/monitoring/grafana/provisioning/dashboards/json/app-metrics-dashboard.json
@@ -0,0 +1,436 @@
+{
+  "annotations": {
+    "list": [
+      {
+        "builtIn": 1,
+        "datasource": {
+          "type": "grafana",
+          "uid": "-- Grafana --"
+        },
+        "enable": true,
+        "hide": true,
+        "iconColor": "rgba(0, 211, 255, 1)",
+        "name": "Annotations & Alerts",
+        "type": "dashboard"
+      }
+    ]
+  },
+  "editable": true,
+  "fiscalYearStartMonth": 0,
+  "graphTooltip": 0,
+  "id": null,
+  "links": [],
+  "liveNow": false,
+  "panels": [
+    {
+      "datasource": {
+        "type": "prometheus",
+        "uid": "prometheus"
+      },
+      "fieldConfig": {
+        "defaults": {
+          "unit": "reqps"
+        },
+        "overrides": []
+      },
+      "gridPos": {
+        "h": 8,
+        "w": 12,
+        "x": 0,
+        "y": 0
+      },
+      "id": 1,
+      "options": {
+        "legend": {
+          "calcs": [],
+          "displayMode": "list",
+          "placement": "bottom",
+          "showLegend": true
+        },
+        "tooltip": {
+          "mode": "single",
+          "sort": "none"
+        }
+      },
+      "targets": [
+        {
+          "datasource": {
+            "type": "prometheus",
+            "uid": "prometheus"
+          },
+          "editorMode": "code",
+          "expr": "sum by (endpoint) (rate(http_requests_total[5m]))",
+          "legendFormat": "{{endpoint}}",
+          "range": true,
+          "refId": "A"
+        }
+      ],
+      "title": "Request Rate by Endpoint",
+      "type": "timeseries"
+    },
+    {
+      "datasource": {
+        "type": "prometheus",
+        "uid": "prometheus"
+      },
+      "fieldConfig": {
+        "defaults": {
+          "unit": "reqps"
+        },
+        "overrides": []
+      },
+      "gridPos": {
+        "h": 8,
+        "w": 12,
+        "x": 12,
+        "y": 0
+      },
+      "id": 2,
+      "options": {
+        "legend": {
+          "calcs": [],
+          "displayMode": "list",
+          "placement": "bottom",
+          "showLegend": true
+        },
+        "tooltip": {
+          "mode": "single",
+          "sort": "none"
+        }
+      },
+      "targets": [
+        {
+          "datasource": {
+            "type": "prometheus",
+            "uid": "prometheus"
+          },
+          "editorMode": "code",
+          "expr": "sum(rate(http_requests_total{status_code=~\"5..\"}[5m]))",
+          "legendFormat": "5xx",
+          "range": true,
+          "refId": "A"
+        }
+      ],
+      "title": "Error Rate (5xx)",
+      "type": "timeseries"
+    },
+    {
+      "datasource": {
+        "type": "prometheus",
+        "uid": "prometheus"
+      },
+      "fieldConfig": {
+        "defaults": {
+          "unit": "s"
+        },
+        "overrides": []
+      },
+      "gridPos": {
+        "h": 8,
+        "w": 12,
+        "x": 0,
+        "y": 8
+      },
+      "id": 3,
+      "options": {
+        "legend": {
+          "calcs": [],
+          "displayMode": "list",
+          "placement": "bottom",
+          "showLegend": false
+        },
+        "tooltip": {
+          "mode": "single",
+          "sort": "none"
+        }
+      },
+      "targets": [
+        {
+          "datasource": {
+            "type": "prometheus",
+            "uid": "prometheus"
+          },
+          "editorMode": "code",
+          "expr": "histogram_quantile(0.95, sum by (le) (rate(http_request_duration_seconds_bucket[5m])))",
+          "legendFormat": "p95",
+          "range": true,
+          "refId": "A"
+        }
+      ],
+      "title": "Request Duration p95",
+      "type": "timeseries"
+    },
+    {
+      "datasource": {
+        "type": "prometheus",
+        "uid": "prometheus"
+      },
+      "fieldConfig": {
+        "defaults": {
+          "unit": "reqps"
+        },
+        "overrides": []
+      },
+      "gridPos": {
+        "h": 8,
+        "w": 12,
+        "x": 12,
+        "y": 8
+      },
+      "id": 4,
+      "options": {
+        "calculate": false,
+        "cellGap": 1,
+        "color": {
+          "mode": "scheme"
+        },
+        "exemplars": {
+          "color": "rgba(255,0,255,0.7)"
+        },
+        "filterValues": {
+          "le": 1e-9
+        },
+        "legend": {
+          "show": false
+        },
+        "rowsFrame": {
+          "layout": "auto"
+        },
+        "showValue": "never",
+        "tooltip": {
+          "show": true,
+          "yHistogram": false
+        },
+        "yAxis": {
+          "axisPlacement": "left",
+          "reverse": false,
+          "unit": "short"
+        }
+      },
+      "targets": [
+        {
+          "datasource": {
+            "type": "prometheus",
+            "uid": "prometheus"
+          },
+          "editorMode": "code",
+          "expr": "sum by (le) (rate(http_request_duration_seconds_bucket[5m]))",
+          "format": "heatmap",
+          "legendFormat": "{{le}}",
+          "range": true,
+          "refId": "A"
+        }
+      ],
+      "title": "Request Duration Heatmap",
+      "type": "heatmap"
+    },
+    {
+      "datasource": {
+        "type": "prometheus",
+        "uid": "prometheus"
+      },
+      "fieldConfig": {
+        "defaults": {
+          "min": 0,
+          "thresholds": {
+            "mode": "absolute",
+            "steps": [
+              {
+                "color": "green",
+                "value": null
+              },
+              {
+                "color": "orange",
+                "value": 5
+              },
+              {
+                "color": "red",
+                "value": 20
+              }
+            ]
+          },
+          "unit": "none"
+        },
+        "overrides": []
+      },
+      "gridPos": {
+        "h": 8,
+        "w": 8,
+        "x": 0,
+        "y": 16
+      },
+      "id": 5,
+      "options": {
+        "orientation": "auto",
+        "reduceOptions": {
+          "calcs": [
+            "lastNotNull"
+          ],
+          "fields": "",
+          "values": false
+        },
+        "showThresholdLabels": false,
+        "showThresholdMarkers": true
+      },
+      "targets": [
+        {
+          "datasource": {
+            "type": "prometheus",
+            "uid": "prometheus"
+          },
+          "editorMode": "code",
+          "expr": "sum(http_requests_in_progress)",
+          "refId": "A"
+        }
+      ],
+      "title": "Active Requests",
+      "type": "gauge"
+    },
+    {
+      "datasource": {
+        "type": "prometheus",
+        "uid": "prometheus"
+      },
+      "fieldConfig": {
+        "defaults": {},
+        "overrides": []
+      },
+      "gridPos": {
+        "h": 8,
+        "w": 8,
+        "x": 8,
+        "y": 16
+      },
+      "id": 6,
+      "options": {
+        "displayLabels": [
+          "name",
+          "percent"
+        ],
+        "legend": {
+          "displayMode": "list",
+          "placement": "right",
+          "showLegend": true
+        },
+        "pieType": "pie",
+        "reduceOptions": {
+          "calcs": [
+            "lastNotNull"
+          ],
+          "fields": "",
+          "values": false
+        }
+      },
+      "targets": [
+        {
+          "datasource": {
+            "type": "prometheus",
+            "uid": "prometheus"
+          },
+          "editorMode": "code",
+          "expr": "sum by (status_code) (rate(http_requests_total[5m]))",
+          "legendFormat": "{{status_code}}",
+          "refId": "A"
+        }
+      ],
+      "title": "Status Code Distribution",
+      "type": "piechart"
+    },
+    {
+      "datasource": {
+        "type": "prometheus",
+        "uid": "prometheus"
+      },
+      "fieldConfig": {
+        "defaults": {
+          "mappings": [
+            {
+              "options": {
+                "0": {
+                  "color": "red",
+                  "index": 0,
+                  "text": "DOWN"
+                },
+                "1": {
+                  "color": "green",
+                  "index": 1,
+                  "text": "UP"
+                }
+              },
+              "type": "value"
+            }
+          ],
+          "thresholds": {
+            "mode": "absolute",
+            "steps": [
+              {
+                "color": "red",
+                "value": null
+              },
+              {
+                "color": "green",
+                "value": 1
+              }
+            ]
+          }
+        },
+        "overrides": []
+      },
+      "gridPos": {
+        "h": 8,
+        "w": 8,
+        "x": 16,
+        "y": 16
+      },
+      "id": 7,
+      "options": {
+        "colorMode": "background",
+        "graphMode": "none",
+        "justifyMode": "center",
+        "orientation": "auto",
+        "reduceOptions": {
+          "calcs": [
+            "lastNotNull"
+          ],
+          "fields": "",
+          "values": false
+        },
+        "textMode": "value_and_name"
+      },
+      "targets": [
+        {
+          "datasource": {
+            "type": "prometheus",
+            "uid": "prometheus"
+          },
+          "editorMode": "code",
+          "expr": "up{job=\"app\"}",
+          "refId": "A"
+        }
+      ],
+      "title": "App Uptime",
+      "type": "stat"
+    }
+  ],
+  "refresh": "10s",
+  "schemaVersion": 40,
+  "style": "dark",
+  "tags": [
+    "lab8",
+    "prometheus",
+    "red"
+  ],
+  "templating": {
+    "list": []
+  },
+  "time": {
+    "from": "now-30m",
+    "to": "now"
+  },
+  "timepicker": {},
+  "timezone": "",
+  "title": "Lab 8 - Application Metrics",
+  "uid": "lab8-app-metrics",
+  "version": 1,
+  "weekStart": ""
+}
diff --git a/monitoring/grafana/provisioning/dashboards/json/logs-dashboard.json b/monitoring/grafana/provisioning/dashboards/json/logs-dashboard.json
new file mode 100644
index 0000000000..1411712d22
--- /dev/null
+++ b/monitoring/grafana/provisioning/dashboards/json/logs-dashboard.json
@@ -0,0 +1,78 @@
+{
+  "annotations": {
+    "list": [
+      {
+        "builtIn": 1,
+        "datasource": {
+          "type": "grafana",
+          "uid": "-- Grafana --"
+        },
+        "enable": true,
+        "hide": true,
+        "iconColor": "rgba(0, 211, 255, 1)",
+        "name": "Annotations & Alerts",
+        "type": "dashboard"
+      }
+    ]
+  },
+  "editable": true,
+  "fiscalYearStartMonth": 0,
+  "graphTooltip": 0,
+  "id": null,
+  "links": [],
+  "panels": [
+    {
+      "datasource": {
+        "type": "loki",
+        "uid": "loki"
+      },
+      "gridPos": {
+        "h": 16,
+        "w": 24,
+        "x": 0,
+        "y": 0
+      },
+      "id": 1,
+      "options": {
+        "dedupStrategy": "none",
+        "enableLogDetails": true,
+        "prettifyLogMessage": false,
+        "showCommonLabels": false,
+        "showLabels": true,
+        "showTime": true,
+        "sortOrder": "Descending",
+        "wrapLogMessage": true
+      },
+      "targets": [
+        {
+          "datasource": {
+            "type": "loki",
+            "uid": "loki"
+          },
+          "editorMode": "code",
+          "expr": "{job=\"docker\"}",
+          "queryType": "range",
+          "refId": "A"
+        }
+      ],
+      "title": "Container Logs",
+      "type": "logs"
+    }
+  ],
+  "refresh": "10s",
+  "schemaVersion": 40,
+  "tags": [
+    "lab7",
+    "loki"
+  ],
+  "templating": {
+    "list": []
+  },
+  "time": {
+    "from": "now-1h",
+    "to": "now"
+  },
+  "title": "Lab 7 - Logs Overview",
+  "uid": "lab7-logs-overview",
+  "version": 1
+}
diff --git a/monitoring/grafana/provisioning/datasources/loki.yml b/monitoring/grafana/provisioning/datasources/datasources.yml
similarity index 50%
rename from monitoring/grafana/provisioning/datasources/loki.yml
rename to monitoring/grafana/provisioning/datasources/datasources.yml
index fba0b1b8e0..259b7dac3a 100644
--- a/monitoring/grafana/provisioning/datasources/loki.yml
+++ b/monitoring/grafana/provisioning/datasources/datasources.yml
@@ -1,10 +1,16 @@
 apiVersion: 1
 
 datasources:
+  - name: Prometheus
+    uid: prometheus
+    type: prometheus
+    access: proxy
+    url: http://prometheus:9090
+    editable: true
+
   - name: Loki
     uid: loki
     type: loki
     access: proxy
     url: http://loki:3100
-    isDefault: true
     editable: true
diff --git a/monitoring/prometheus/prometheus.yml b/monitoring/prometheus/prometheus.yml
new file mode 100644
index 0000000000..f155272a88
--- /dev/null
+++ b/monitoring/prometheus/prometheus.yml
@@ -0,0 +1,23 @@
+global:
+  scrape_interval: 15s
+  evaluation_interval: 15s
+
+scrape_configs:
+  - job_name: 'prometheus'
+    static_configs:
+      - targets: ['localhost:9090']
+
+  - job_name: 'app'
+    metrics_path: '/metrics'
+    static_configs:
+      - targets: ['app-python:8000']
+
+  - job_name: 'loki'
+    metrics_path: '/metrics'
+    static_configs:
+      - targets: ['loki:3100']
+
+  - job_name: 'grafana'
+    metrics_path: '/metrics'
+    static_configs:
+      - targets: ['grafana:3000']
diff --git a/monitoring/promtail/config.yml b/monitoring/promtail/config.yml
index 9bcb08d656..949c79ff77 100644
--- a/monitoring/promtail/config.yml
+++ b/monitoring/promtail/config.yml
@@ -13,12 +13,12 @@ scrape_configs:
     docker_sd_configs:
       - host: unix:///var/run/docker.sock
         refresh_interval: 5s
-        filters:
-          - name: label
-            values: ["logging=promtail"]
     pipeline_stages:
       - docker: {}
     relabel_configs:
+      - source_labels: ["__meta_docker_container_label_logging"]
+        regex: promtail
+        action: keep
       - source_labels: ["__meta_docker_container_name"]
         regex: "/(.*)"
         target_label: container