diff --git a/.github/workflows/ci.yml b/.github/workflows/ci.yml
index e97e1f4..1df98c7 100644
--- a/.github/workflows/ci.yml
+++ b/.github/workflows/ci.yml
@@ -2,21 +2,56 @@ name: CI
 
 on:
   push:
-    branches: [ "main" ]
+    branches: ["main"]
   pull_request:
 
 jobs:
-  build:
+  test:
     runs-on: ubuntu-latest
+
+    strategy:
+      fail-fast: false
+      matrix:
+        python-version: ["3.10", "3.11", "3.12"]
+
     steps:
       - uses: actions/checkout@v4
+
       - uses: actions/setup-python@v5
         with:
-          python-version: "3.11"
-      - name: Install
+          python-version: ${{ matrix.python-version }}
+
+      - name: Install package
         run: |
           python -m pip install --upgrade pip
           python -m pip install -e .
+
       - name: Import check
         run: |
-          python -c "import multiverse; from multiverse.datasets import list_datasets; print(list_datasets())"
+          python -c "import multiverse; print(multiverse.__file__)"
+
+      - name: Basic package check
+        run: |
+          python -c "import importlib.metadata as md; print(md.version('aeon-multiverse'))"
+
+  build:
+    runs-on: ubuntu-latest
+
+    steps:
+      - uses: actions/checkout@v4
+
+      - uses: actions/setup-python@v5
+        with:
+          python-version: "3.11"
+
+      - name: Install build tools
+        run: |
+          python -m pip install --upgrade pip build twine
+
+      - name: Build package
+        run: |
+          python -m build
+
+      - name: Check built distributions
+        run: |
+          twine check dist/*
\ No newline at end of file
diff --git a/experiments/run_benchmark.py b/experiments/run_benchmark.py
index 0047940..a89fbba 100644
--- a/experiments/run_benchmark.py
+++ b/experiments/run_benchmark.py
@@ -6,28 +6,20 @@
 import time
 
 import pandas as pd
-from aeon.classification.interval_based import TimeSeriesForestClassifier
+from aeon.classification.convolution_based import RocketClassifier
 
-from multiverse.datasets import list_datasets, load_dataset
-
-
-def main():
-    ap = argparse.ArgumentParser()
-    ap.add_argument("--datasets", default="all", help="Comma-separated list, or 'all'")
-    ap.add_argument("--out", default="benchmark_results.csv")
-    args = ap.parse_args()
-
-    if args.datasets.strip().lower() == "all":
-        datasets = list_datasets()
-    else:
-        datasets = [d.strip() for d in args.datasets.split(",") if d.strip()]
+from aeon.datasets import load_classification
+from aeon.datasets.tsc_datasets import multivariate_equal_length
 
+def experiment_example():
+    datasets = ["BasicMotions"]
     rows = []
     for name in datasets:
-        X_train, y_train = load_dataset(name, "train")
-        X_test, y_test = load_dataset(name, "test")
+        X_train, y_train = load_classification(name, "train")
+        X_test, y_test = load_classification(name, "test")
+
+        clf = RocketClassifier(n_kernels=500, random_state=0)
 
-        clf = TimeSeriesForestClassifier(n_estimators=200, random_state=0)
 
         t0 = time.time()
         clf.fit(X_train, y_train)
@@ -52,4 +44,4 @@ def main():
 
 
 if __name__ == "__main__":
-    main()
+    experiment_example()