diff --git a/.travis.yml b/.travis.yml
new file mode 100644
index 000000000..67fdd3d0d
--- /dev/null
+++ b/.travis.yml
@@ -0,0 +1,16 @@
+# https://docs.travis-ci.com/user/languages/python/
+language: python
+python:
+  - "2.7"
+  - "3.6"
+install:
+  - pip install tensorflow
+  - pip install .
+script:
+  # units test
+  # https://docs.pytest.org/en/latest/
+  # TODO: make it work
+  # - pytest
+
+  # smoke tests
+  - python example/tutorial_mnist_tiny.py
diff --git a/example/tutorial_mnist_tiny.py b/example/tutorial_mnist_tiny.py
new file mode 100644
index 000000000..b7891a55d
--- /dev/null
+++ b/example/tutorial_mnist_tiny.py
@@ -0,0 +1,60 @@
+#! /usr/bin/python
+# -*- coding: utf-8 -*-
+
+
+
+import tensorflow as tf
+import tensorlayer as tl
+
+sess = tf.InteractiveSession()
+
+# prepare data
+X_train, y_train, X_val, y_val, X_test, y_test = \
+                                tl.files.load_mnist_dataset(shape=(-1,784))
+# define placeholder
+x = tf.placeholder(tf.float32, shape=[None, 784], name='x')
+y_ = tf.placeholder(tf.int64, shape=[None, ], name='y_')
+
+# define the network
+network = tl.layers.InputLayer(x, name='input')
+network = tl.layers.DropoutLayer(network, keep=0.8, name='drop1')
+network = tl.layers.DenseLayer(network, 800, tf.nn.relu, name='relu1')
+network = tl.layers.DropoutLayer(network, keep=0.5, name='drop2')
+network = tl.layers.DenseLayer(network, 800, tf.nn.relu, name='relu2')
+network = tl.layers.DropoutLayer(network, keep=0.5, name='drop3')
+# the softmax is implemented internally in tl.cost.cross_entropy(y, y_) to
+# speed up computation, so we use identity here.
+# see tf.nn.sparse_softmax_cross_entropy_with_logits()
+network = tl.layers.DenseLayer(network, n_units=10,
+                                act=tf.identity, name='output')
+
+# define cost function and metric.
+y = network.outputs
+cost = tl.cost.cross_entropy(y, y_, name='cost')
+correct_prediction = tf.equal(tf.argmax(y, 1), y_)
+acc = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))
+y_op = tf.argmax(tf.nn.softmax(y), 1)
+
+# define the optimizer
+train_params = network.all_params
+train_op = tf.train.AdamOptimizer(learning_rate=0.0001
+                    ).minimize(cost, var_list=train_params)
+
+# initialize all variables in the session
+tl.layers.initialize_global_variables(sess)
+
+# print network information
+network.print_params()
+network.print_layers()
+
+# train the network
+tl.utils.fit(sess, network, train_op, cost, X_train, y_train, x, y_,
+            acc=acc, batch_size=500, n_epoch=5, print_freq=5,
+            X_val=X_val, y_val=y_val, eval_train=False)
+
+# evaluation
+tl.utils.test(sess, network, acc, X_test, y_test, x, y_, batch_size=None, cost=cost)
+
+# save the network to .npz file
+tl.files.save_npz(network.all_params , name='model.npz')
+sess.close()