diff --git a/.github/workflows/maint-78-model-evaluation-pilot.yml b/.github/workflows/maint-78-model-evaluation-pilot.yml
index b559920c3..7f3836f00 100644
--- a/.github/workflows/maint-78-model-evaluation-pilot.yml
+++ b/.github/workflows/maint-78-model-evaluation-pilot.yml
@@ -24,10 +24,16 @@ jobs:
           OPENAI_API_KEY: ${{ secrets.OPENAI_API_KEY }}
           CLAUDE_API_STRANSKE: ${{ secrets.CLAUDE_API_STRANSKE }}
         run: |
-          uv run --extra dev python tools/run_model_eval_pilot.py --output pilot-results.json
+          uv run --extra dev python -m tools.run_model_eval_pilot --output pilot-results.json
       - name: Summarize pilot
         if: always()
         run: |
+          if [ ! -f pilot-results.json ]; then
+            echo '## Verifier model pilot' >> "$GITHUB_STEP_SUMMARY"
+            echo 'The pilot failed before producing a results artifact; inspect the run step.' \
+              >> "$GITHUB_STEP_SUMMARY"
+            exit 0
+          fi
           {
             echo '## Verifier model pilot'
             echo 'The pilot narrows candidates only; approval still requires the 75-case corpus.'
@@ -43,4 +49,4 @@ jobs:
           name: verifier-model-pilot-${{ github.run_id }}
           path: |
             pilot-results.json
-          if-no-files-found: error
+          if-no-files-found: warn
diff --git a/tests/workflows/test_model_eval_pilot_workflow.py b/tests/workflows/test_model_eval_pilot_workflow.py
new file mode 100644
index 000000000..5a37bce8e
--- /dev/null
+++ b/tests/workflows/test_model_eval_pilot_workflow.py
@@ -0,0 +1,21 @@
+from pathlib import Path
+
+import yaml
+
+
+def test_model_eval_pilot_runs_as_importable_module() -> None:
+    root = Path(__file__).resolve().parents[2]
+    workflow = yaml.safe_load(
+        (root / ".github/workflows/maint-78-model-evaluation-pilot.yml").read_text(encoding="utf-8")
+    )
+    steps = workflow["jobs"]["pilot"]["steps"]
+    pilot = next(step for step in steps if step.get("name") == "Run paired 30-case pilot")
+    summary = next(step for step in steps if step.get("name") == "Summarize pilot")
+    upload = next(step for step in steps if "actions/upload-artifact@" in step.get("uses", ""))
+
+    assert pilot["run"].count("python -m tools.run_model_eval_pilot") == 1
+    assert "python tools/run_model_eval_pilot.py" not in pilot["run"]
+    assert summary["if"] == "always()"
+    assert "if [ ! -f pilot-results.json ]" in summary["run"]
+    assert upload["if"] == "always()"
+    assert upload["with"]["if-no-files-found"] == "warn"