diff --git a/Makefile b/Makefile
index c12f88b63..bc99b57d0 100644
--- a/Makefile
+++ b/Makefile
@@ -319,7 +319,7 @@ install-test: | install-test-setup
 	$(call pytest,--no-success-flaky-report --benchmark-disable -n auto -k "not fuzz" --durations=5)
 
 examples-test:
-	cd examples && pytest --no-success-flaky-report --benchmark-disable -n auto --durations=5 . --cov=compiler_gym --cov-report=xml:$(COV_REPORT) $(PYTEST_ARGS)
+	cd examples && pytest --nbmake --no-success-flaky-report --benchmark-disable -n auto --durations=5 . --cov=compiler_gym --cov-report=xml:$(COV_REPORT) $(PYTEST_ARGS)
 
 # Note we export $CI=1 so that the tests always run as if within the CI
 # environement. This is to ensure that the reported coverage matches that of
diff --git a/tests/requirements.txt b/tests/requirements.txt
index 623fd95ef..28c85e55e 100644
--- a/tests/requirements.txt
+++ b/tests/requirements.txt
@@ -1,4 +1,5 @@
 flaky==3.7.0
+nbmake==0.10
 psutil==5.8.0  # Implicit dependency of pytest-xdist
 pytest==6.1.0
 pytest-benchmark==3.2.3