diff --git a/.env.example b/.env.example
index f147629..8e4f793 100644
--- a/.env.example
+++ b/.env.example
@@ -1,5 +1,5 @@
 # Copy to .env (git-ignored). Never commit real values.
-DBRICKS_HOST=adb-xxxx.azuredatabricks.net
-DBRICKS_HTTP_PATH=/sql/1.0/warehouses/xxxxxxxx
-DBRICKS_TOKEN=dapi...your-token-here
+DATABRICKS_HOST=adb-xxxx.azuredatabricks.net
+DATABRICKS_HTTP_PATH=/sql/1.0/warehouses/xxxxxxxx
+DATABRICKS_TOKEN=dapi...your-token-here
 DBT_SCHEMA=dev_yourname
diff --git a/.github/workflows/pr-body-check.yml b/.github/workflows/pr-body-check.yml
new file mode 100644
index 0000000..f6109aa
--- /dev/null
+++ b/.github/workflows/pr-body-check.yml
@@ -0,0 +1,57 @@
+name: PR body check
+
+# Fails the check when a pull request description is missing the sections from
+# .github/PULL_REQUEST_TEMPLATE.md. GitHub only auto-fills that template in the
+# web "compose" form and in `gh pr create` with no --body; a PR opened through
+# the REST API or `gh pr create --body "..."` (the path most AI tools take)
+# silently skips it. This check is the only thing that actually enforces it.
+#
+# Uses pull_request_target (in addition to pull_request) so fork PRs always run
+# the workflow from main. The job only reads github.event.pull_request.body —
+# it does not check out PR head code.
+#
+# Recovery is automatic: editing the PR description fires the `edited` event and
+# re-runs this check with the new body. No new commit or manual re-run needed.
+
+on:
+  pull_request:
+    types: [opened, edited, reopened, synchronize]
+    branches: [main]
+  pull_request_target:
+    types: [opened, edited, reopened, synchronize]
+    branches: [main]
+
+permissions:
+  contents: read
+
+jobs:
+  check:
+    runs-on: ubuntu-latest
+    steps:
+      - name: Check required sections are present
+        env:
+          PR_BODY: ${{ github.event.pull_request.body }}
+        run: |
+          set -euo pipefail
+          required=(
+            "## Summary"
+            "## How to review"
+            "## Secrets hygiene checklist"
+          )
+          missing=()
+          for section in "${required[@]}"; do
+            if ! printf '%s' "$PR_BODY" | grep -qiF "$section"; then
+              missing+=("$section")
+            fi
+          done
+          if [ ${#missing[@]} -ne 0 ]; then
+            echo "::error::Your PR description is missing required sections. Start from the template (.github/PULL_REQUEST_TEMPLATE.md) and keep these headings:"
+            for m in "${missing[@]}"; do echo "  - $m"; done
+            echo ""
+            echo "If you (or an AI tool) opened this PR without the template, click 'Edit' on the"
+            echo "PR description, paste the template, and fill it in. Editing the description"
+            echo "re-runs this check automatically. A complete PR is easy to review and"
+            echo "reproducible: that is part of the assignment."
+            exit 1
+          fi
+          echo "All required PR sections present."
diff --git a/README.md b/README.md
index c6ed11b..cefafb5 100644
--- a/README.md
+++ b/README.md
@@ -31,6 +31,7 @@ data-assignment-week-13/
 ├── task-3/                          # Git-backed Job scheduling
 │   ├── SCHEDULING.md                # Jobs vs Airflow write-up + Job Run URL
 │   └── screenshots/                 # Job config, green run, paused trigger
+├── task-4/                          # optional bonuses only (create if needed)
 ├── .env.example
 ├── AI_ASSIST.md                     # LLM interaction log
 └── README.md
diff --git a/task-1/README.md b/task-1/README.md
index 9a1b2af..973f050 100644
--- a/task-1/README.md
+++ b/task-1/README.md
@@ -11,4 +11,4 @@ Add your Databricks notebook here.
 - Results displayed with `show()` on small aggregated DataFrames (not `collect()` on the raw table).
 - Two or three sentences on when you would choose PySpark versus dbt SQL.
 
-See the [Week 13 assignment](https://github.com/HackYourFuture/datatrack/blob/main/Data%20Track/Week%2013/week_13__6_assignment.md) for full requirements.
+See the [Week 13 assignment](https://github.com/HackYourFuture/datatrack/blob/main/Data%20Track/Week%2013/week_13__7_assignment.md) for full requirements.
diff --git a/task-2/README.md b/task-2/README.md
index e5951e5..5706176 100644
--- a/task-2/README.md
+++ b/task-2/README.md
@@ -7,6 +7,6 @@ Copy your **Week 10 dbt project** into this folder (or start from the `week-13-d
 1. Install `dbt-databricks` locally (`pip install dbt-databricks` or `uv tool install dbt-databricks`).
 2. Copy `profiles.yml.example` to `profiles.yml` (git-ignored) and export the env vars from `.env.example`.
 3. Configure `fct_trips` as `materialized='incremental'` with `incremental_strategy='merge'` and a real `unique_key`.
-4. Run `dbt build --select fct_trips` twice and document both timings plus your explanation in `WRITEUP.md`.
+4. Run `dbt build --select fct_trips --full-refresh` for the baseline, then `dbt build --select fct_trips` for the incremental rerun. Document both timings plus your explanation in `WRITEUP.md`.
 
 **Do not commit:** `profiles.yml`, `.env`, or any Databricks token.
diff --git a/task-2/profiles.yml.example b/task-2/profiles.yml.example
index 557e82e..ab26809 100644
--- a/task-2/profiles.yml.example
+++ b/task-2/profiles.yml.example
@@ -6,7 +6,7 @@ nyc_taxi:
       type: databricks
       catalog: hyf
       schema: "{{ env_var('DBT_SCHEMA') }}"
-      host: "{{ env_var('DBRICKS_HOST') }}"
-      http_path: "{{ env_var('DBRICKS_HTTP_PATH') }}"
-      token: "{{ env_var('DBRICKS_TOKEN') }}"
+      host: "{{ env_var('DATABRICKS_HOST') }}"
+      http_path: "{{ env_var('DATABRICKS_HTTP_PATH') }}"
+      token: "{{ env_var('DATABRICKS_TOKEN') }}"
       threads: 4