diff --git a/.github/workflows/examples.yml b/.github/workflows/examples.yml
index 3f34ebe..4ac7168 100644
--- a/.github/workflows/examples.yml
+++ b/.github/workflows/examples.yml
@@ -27,16 +27,7 @@ jobs:
         run: poetry install --all-extras
 
       - name: Run all example scripts
-        run: |
-          # Find all Python files in examples directory
-          find examples -name "*.py" -type f | while read -r script; do
-            echo "Running example: $script"
-            poetry run python "$script"
-            if [ $? -ne 0 ]; then
-              echo "Error: Failed to run $script"
-              exit 1
-            fi
-          done
+        run: ARGS="-vv" make test.examples
         env:
           WORKFLOWAI_API_KEY: ${{ secrets.WORKFLOWAI_TEST_API_KEY }}
 
diff --git a/Makefile b/Makefile
index 9c2bd9f..2fc8a61 100644
--- a/Makefile
+++ b/Makefile
@@ -31,3 +31,6 @@ test:
 .PHONY: lock
 lock:
 	poetry lock --no-update
+
+test.examples:
+	poetry run pytest examples -n=5 ${ARGS}
diff --git a/examples/17_multi_model_consensus_with_tools.py b/examples/17_multi_model_consensus_with_tools.py
index 82806f4..ccf16d7 100644
--- a/examples/17_multi_model_consensus_with_tools.py
+++ b/examples/17_multi_model_consensus_with_tools.py
@@ -20,6 +20,7 @@
 
 import asyncio
 
+import pytest
 from pydantic import BaseModel, Field
 
 import workflowai
@@ -131,6 +132,7 @@ async def combine_responses(responses_input: CombinerInput) -> CombinedOutput:
     ...
 
 
+@pytest.mark.xfail(reason="Example is flaky")
 async def main():
     # Example: Scientific explanation
     print("\nExample: Scientific Concept")
diff --git a/examples/workflows/agent_delegation.py b/examples/workflows/agent_delegation.py
index 91630e0..bf6dde9 100644
--- a/examples/workflows/agent_delegation.py
+++ b/examples/workflows/agent_delegation.py
@@ -17,6 +17,7 @@
 import asyncio
 from typing import Optional
 
+import pytest
 from pydantic import BaseModel, Field
 
 import workflowai
@@ -118,7 +119,7 @@ async def delegate_task(agent_input: DelegateInput) -> DelegateOutput:
 
 @workflowai.agent(
     id="orchestrator",
-    model=Model.GPT_4O_LATEST,
+    model=Model.GEMINI_2_0_FLASH_LATEST,
     tools=[delegate_task],
 )
 async def orchestrator_agent(agent_input: OrchestratorInput) -> OrchestratorOutput:
@@ -148,6 +149,7 @@ async def orchestrator_agent(agent_input: OrchestratorInput) -> OrchestratorOutp
     ...
 
 
+@pytest.mark.xfail(reason="Example is flaky")
 async def main():
     # Example: Software architecture task
     print("\nExample: Software Architecture Design")
diff --git a/poetry.lock b/poetry.lock
index 39ae623..9093781 100644
--- a/poetry.lock
+++ b/poetry.lock
@@ -1,4 +1,4 @@
-# This file is automatically @generated by Poetry 1.8.3 and should not be changed by hand.
+# This file is automatically @generated by Poetry 1.8.5 and should not be changed by hand.
 
 [[package]]
 name = "annotated-types"
@@ -105,6 +105,20 @@ files = [
 [package.extras]
 test = ["pytest (>=6)"]
 
+[[package]]
+name = "execnet"
+version = "2.1.1"
+description = "execnet: rapid multi-Python deployment"
+optional = false
+python-versions = ">=3.8"
+files = [
+    {file = "execnet-2.1.1-py3-none-any.whl", hash = "sha256:26dee51f1b80cebd6d0ca8e74dd8745419761d3bef34163928cbebbdc4749fdc"},
+    {file = "execnet-2.1.1.tar.gz", hash = "sha256:5189b52c6121c24feae288166ab41b32549c7e2348652736540b9e6e7d4e72e3"},
+]
+
+[package.extras]
+testing = ["hatch", "pre-commit", "pytest", "tox"]
+
 [[package]]
 name = "filelock"
 version = "3.17.0"
@@ -560,6 +574,26 @@ pytest = "==8.*"
 [package.extras]
 testing = ["pytest-asyncio (==0.24.*)", "pytest-cov (==6.*)"]
 
+[[package]]
+name = "pytest-xdist"
+version = "3.6.1"
+description = "pytest xdist plugin for distributed testing, most importantly across multiple CPUs"
+optional = false
+python-versions = ">=3.8"
+files = [
+    {file = "pytest_xdist-3.6.1-py3-none-any.whl", hash = "sha256:9ed4adfb68a016610848639bb7e02c9352d5d9f03d04809919e2dafc3be4cca7"},
+    {file = "pytest_xdist-3.6.1.tar.gz", hash = "sha256:ead156a4db231eec769737f57668ef58a2084a34b2e55c4a8fa20d861107300d"},
+]
+
+[package.dependencies]
+execnet = ">=2.1"
+pytest = ">=7.0.0"
+
+[package.extras]
+psutil = ["psutil (>=3.0)"]
+setproctitle = ["setproctitle"]
+testing = ["filelock"]
+
 [[package]]
 name = "python-dateutil"
 version = "2.9.0.post0"
@@ -821,4 +855,4 @@ test = ["covdefaults (>=2.3)", "coverage (>=7.2.7)", "coverage-enable-subprocess
 [metadata]
 lock-version = "2.0"
 python-versions = "^3.9"
-content-hash = "5116675c3d4551c562da2dd230d9497cc16085b171fc72cc48bb2868c98acfba"
+content-hash = "b0baf6026dcfd737e370df10f839c3ee0fc094a36d892b673ec5217af3287ffc"
diff --git a/pyproject.toml b/pyproject.toml
index f587ce7..64d2952 100644
--- a/pyproject.toml
+++ b/pyproject.toml
@@ -20,6 +20,7 @@ ruff = "^0.9.6"
 freezegun = "^1.5.1"
 pre-commit = "^4.0.1"
 pytest-httpx = "^0.35.0"
+pytest-xdist = "^3.1.0"
 python-dotenv = "^1.0.1"
 typer = "^0.15.1"
 rich = "^13.7.1"