diff --git a/tests/e2e/run_e2e_tests.sh b/tests/e2e/run_e2e_tests.sh
index c24931f4..a164b7f9 100644
--- a/tests/e2e/run_e2e_tests.sh
+++ b/tests/e2e/run_e2e_tests.sh
@@ -21,10 +21,11 @@ trap 'print_debug' INT TERM ERR
 
 log starting > ../build.log
 
-log building and running function_calling demo
+log starting weather_forecast agent natively
 log ===========================================
 cd ../../demos/getting_started/weather_forecast/
-docker compose up weather_forecast_service --build -d
+bash start_agents.sh &
+AGENTS_PID=$!
 cd -
 
 log building and installing plano cli
@@ -78,8 +79,6 @@ log running e2e tests for openai responses api client
 log ========================================
 uv run pytest test_openai_responses_api_client_with_state.py
 
-log shutting down the weather_forecast demo
+log shutting down the weather_forecast agent
 log =======================================
-cd ../../demos/getting_started/weather_forecast
-docker compose down
-cd -
+kill $AGENTS_PID 2>/dev/null || true
diff --git a/tests/e2e/run_prompt_gateway_tests.sh b/tests/e2e/run_prompt_gateway_tests.sh
index 58d850d8..1e947813 100755
--- a/tests/e2e/run_prompt_gateway_tests.sh
+++ b/tests/e2e/run_prompt_gateway_tests.sh
@@ -32,10 +32,11 @@ cd -
 # Re-sync e2e deps
 uv sync
 
-# Start weather_forecast service (needed for prompt_gateway tests)
-log "building and running weather_forecast service"
+# Start weather_forecast service natively (needed for prompt_gateway tests)
+log "starting weather_forecast agent natively"
 cd ../../demos/getting_started/weather_forecast/
-docker compose up weather_forecast_service --build -d
+bash start_agents.sh &
+AGENTS_PID=$!
 cd -
 
 # Start gateway with prompt_gateway config
@@ -52,6 +53,4 @@ uv run pytest test_prompt_gateway.py
 # Cleanup
 log "shutting down"
 planoai down --docker || true
-cd ../../demos/getting_started/weather_forecast
-docker compose down
-cd -
+kill $AGENTS_PID 2>/dev/null || true