diff --git a/.coveragerc b/.coveragerc
index e28fb8aff463a8f3c127a11c410b2dbbd397ee01..23be84dd8ea932c420fe3e44f9a804af79ca8523 100644
--- a/.coveragerc
+++ b/.coveragerc
@@ -2,5 +2,6 @@
 omit = 
 	*/Colonel/*
 	topfarm/tests/*
+	topfarm/workshop.py
 [report]
 fail_under = 95
\ No newline at end of file
diff --git a/examples/workshop/workshop_competition.ipynb b/examples/workshop/workshop_competition.ipynb
new file mode 100644
index 0000000000000000000000000000000000000000..cadf6fba4a74c2ec5e1b3267f4c3448eb4128bcb
--- /dev/null
+++ b/examples/workshop/workshop_competition.ipynb
@@ -0,0 +1,398 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "colab_type": "text",
+    "id": "2UutOYHh1G8e"
+   },
+   "source": [
+    "# Step 1: Install Topfarm and dependencies\n",
+    "(don't change anything here)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 34,
+   "metadata": {
+    "colab": {},
+    "colab_type": "code",
+    "id": "-KukrdmrO37J"
+   },
+   "outputs": [],
+   "source": [
+    "%%capture\n",
+    "try:\n",
+    "    import topfarm\n",
+    "except ImportError as e:\n",
+    "    !pip install topfarm\n",
+    "try:\n",
+    "    import py_wake\n",
+    "except ImportError as e:\n",
+    "    !pip install py_wake\n",
+    "try:\n",
+    "    import networkx\n",
+    "except ImportError as e:\n",
+    "    !pip install networkx==2.1\n",
+    "import networkx\n",
+    "if networkx.__version__ > '2.1':\n",
+    "    print('Current version of OpenMDAO only supports networkx-version up to 2.1')"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# Step 2: Import dependencies\n",
+    "(don't change anything here)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 16,
+   "metadata": {
+    "colab": {},
+    "colab_type": "code",
+    "id": "luuQrGgNSUJB"
+   },
+   "outputs": [],
+   "source": [
+    "%matplotlib inline\n",
+    "import numpy as np\n",
+    "import topfarm\n",
+    "import matplotlib.pyplot as plt\n",
+    "from topfarm.workshop import report_result, plot_result"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# Step 3: Import site data, wind turbine data and chose desired wake model from py_wake\n",
+    "(don't change anything here)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 35,
+   "metadata": {
+    "colab": {},
+    "colab_type": "code",
+    "id": "LeAWjyUJPICd"
+   },
+   "outputs": [],
+   "source": [
+    "from py_wake.examples.data.iea37 import IEA37Site, IEA37_WindTurbines\n",
+    "from py_wake.wake_models import IEA37SimpleBastankhahGaussian\n",
+    "from topfarm.cost_models.py_wake_wrapper import PyWakeAEP\n",
+    "\n",
+    "windTurbines = IEA37_WindTurbines()\n",
+    "wake_model = IEA37SimpleBastankhahGaussian(windTurbines) \n",
+    "n_wt = 16\n",
+    "site = IEA37Site(n_wt)\n",
+    "site.default_ws = [9.8]\n",
+    "site.default_wd = np.arange(0,360,22.5)\n",
+    "aep_calc = PyWakeAEP(site, windTurbines, wake_model)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 36,
+   "metadata": {
+    "colab": {
+     "base_uri": "https://localhost:8080/",
+     "height": 286
+    },
+    "colab_type": "code",
+    "id": "Rrcdi9yF0bmg",
+    "outputId": "97ef5dc5-362f-40fa-90ee-104f5f248388"
+   },
+   "outputs": [
+    {
+     "data": {
+      "image/png": "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\n",
+      "text/plain": [
+       "<Figure size 432x288 with 1 Axes>"
+      ]
+     },
+     "metadata": {
+      "needs_background": "light"
+     },
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "site.plot_wd_distribution(len(site.default_wd))"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# Step 4: Set up a Topfarm optimization problem\n",
+    "(don't change anything here)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 19,
+   "metadata": {
+    "colab": {},
+    "colab_type": "code",
+    "id": "ykw6CyYrRBGw"
+   },
+   "outputs": [],
+   "source": [
+    "from topfarm import TopFarmProblem\n",
+    "from topfarm.constraint_components.boundary import CircleBoundaryConstraint\n",
+    "from topfarm.plotting import XYPlotComp, NoPlot\n",
+    "\n",
+    "def get_topfarm(driver, plot=False):\n",
+    "  return TopFarmProblem(\n",
+    "    design_vars=dict(zip('xy', site.initial_position.T*.99)),\n",
+    "    cost_comp=aep_calc.get_TopFarm_cost_component(16),\n",
+    "    driver=driver,\n",
+    "    constraints=[CircleBoundaryConstraint([0, 0], 1300)],\n",
+    "    plot_comp=(NoPlot(), XYPlotComp())[plot]\n",
+    "  )\n"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "colab_type": "text",
+    "id": "0qLS6NshRezf"
+   },
+   "source": [
+    "# Step 5: Choose a driver\n",
+    "Below you will find a list of currently implemented drivers. Pick one and tune it, but changing the arguemnts to get your first optimization results."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 41,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Please enter your name for the scorboard: Mikkel\n"
+     ]
+    }
+   ],
+   "source": [
+    "your_name = input('Please enter your name for the scorboard: ')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "colab": {},
+    "colab_type": "code",
+    "id": "5sgHB_J1U5S_"
+   },
+   "outputs": [],
+   "source": [
+    "from topfarm.easy_drivers import EasyRandomSearchDriver, EasyScipyOptimizeDriver, EasySimpleGADriver\n",
+    "from topfarm.drivers.random_search_driver import RandomizeTurbinePosition_Circle, RandomizeTurbinePosition_Square\n",
+    "\n",
+    "drivers = [\n",
+    "    EasyScipyOptimizeDriver(optimizer='SLSQP',maxiter=10, disp=False),\n",
+    "    EasyRandomSearchDriver(randomize_func=RandomizeTurbinePosition_Circle(max_step=None), max_iter=100),\n",
+    "    EasyRandomSearchDriver(randomize_func=RandomizeTurbinePosition_Square(max_step=None), max_iter=100),\n",
+    "    EasySimpleGADriver(max_gen=100, pop_size=80, Pm=0),\n",
+    "]\n",
+    "driver_no = 2"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "colab": {
+     "base_uri": "https://localhost:8080/",
+     "height": 34
+    },
+    "colab_type": "code",
+    "id": "_DYdoipfVj3X",
+    "outputId": "e35cda74-c0a0-471f-a5f9-bc13697a4868"
+   },
+   "outputs": [],
+   "source": [
+    "@report_result(your_name)\n",
+    "def test():\n",
+    "  driver = drivers[driver_no]\n",
+    "  tf = get_topfarm(driver)\n",
+    "  return tf.optimize()\n",
+    "\n",
+    "cost, state, recorder = test()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# Step 6: Take a look at your optimized configuration"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 23,
+   "metadata": {
+    "colab": {
+     "base_uri": "https://localhost:8080/",
+     "height": 696
+    },
+    "colab_type": "code",
+    "id": "bZ_vv-Gh-We3",
+    "outputId": "ff893546-9bfd-4029-b653-3b335f021f16"
+   },
+   "outputs": [
+    {
+     "data": {
+      "image/png": "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\n",
+      "text/plain": [
+       "<Figure size 432x288 with 1 Axes>"
+      ]
+     },
+     "metadata": {
+      "needs_background": "light"
+     },
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "text/plain": [
+       "(-384.20990791837886,\n",
+       " {'x': array([  503.92177963,   715.46792419,     3.45351766,  -520.60239   ,\n",
+       "          -459.54142359,    33.61842405,  1287.        ,  1041.204879  ,\n",
+       "           397.704879  ,  -397.704879  , -1041.204879  ,  -691.11204214,\n",
+       "         -1041.204879  ,  -298.59361329,  -867.37058181,  1041.204879  ]),\n",
+       "  'y': array([  111.69872343,  -942.08758939,  1015.50390169,   378.239796  ,\n",
+       "          -357.00624372,  -530.25318724,     0.        ,   756.479592  ,\n",
+       "          1224.009765  ,  1224.009765  ,   756.479592  ,   889.49628969,\n",
+       "          -756.479592  , -1258.38483507,  -120.73095824,  -756.479592  ])})"
+      ]
+     },
+     "execution_count": 23,
+     "metadata": {},
+     "output_type": "execute_result"
+    },
+    {
+     "data": {
+      "image/png": "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\n",
+      "text/plain": [
+       "<Figure size 432x288 with 1 Axes>"
+      ]
+     },
+     "metadata": {
+      "needs_background": "light"
+     },
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "tf = get_topfarm(drivers[driver_no], plot=True)\n",
+    "tf.evaluate() # plot initial state\n",
+    "tf.evaluate(state) # plot final state"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# Step 7: Now try with several optimizers running in succession:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "colab": {},
+    "colab_type": "code",
+    "id": "h_9D6PCd2imr"
+   },
+   "outputs": [],
+   "source": [
+    "@report_result(your_name)\n",
+    "def test():\n",
+    "  tf = get_topfarm(EasyRandomSearchDriver(randomize_func=RandomizeTurbinePosition_Circle(), max_iter=100000))\n",
+    "  cost, state, recorder = tf.optimize()\n",
+    "  \n",
+    "  driver = EasyScipyOptimizeDriver(optimizer='SLSQP',tol=1e-10, maxiter=300)\n",
+    "  tf2 = get_topfarm(driver)\n",
+    "  return tf2.optimize(state)\n",
+    "\n",
+    "cost, state, recorder = test()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# Step 8: Take a look at the scoreboard to see how your are doing"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 55,
+   "metadata": {
+    "colab": {
+     "base_uri": "https://localhost:8080/",
+     "height": 606
+    },
+    "colab_type": "code",
+    "id": "WSVLt-dYY1bN",
+    "outputId": "9de53bdd-13d1-4c6c-b085-e39468eae673"
+   },
+   "outputs": [
+    {
+     "data": {
+      "image/png": "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\n",
+      "text/plain": [
+       "<Figure size 1800x720 with 1 Axes>"
+      ]
+     },
+     "metadata": {
+      "needs_background": "light"
+     },
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "# plot all results\n",
+    "fig = plot_result()\n",
+    "plt.show()"
+   ]
+  }
+ ],
+ "metadata": {
+  "colab": {
+   "collapsed_sections": [],
+   "name": "Topfarm.ipynb",
+   "provenance": [],
+   "version": "0.3.2"
+  },
+  "kernelspec": {
+   "display_name": "Python 3",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.6.8"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 1
+}
diff --git a/topfarm/workshop.py b/topfarm/workshop.py
new file mode 100644
index 0000000000000000000000000000000000000000..a4a623c41f9f57beaa124b9a499210cddefc3307
--- /dev/null
+++ b/topfarm/workshop.py
@@ -0,0 +1,66 @@
+from urllib.request import urlopen, Request
+from urllib.parse import urlencode
+import time
+from _collections import defaultdict
+import matplotlib.pyplot as plt
+import numpy as np
+
+
+def report_result(name, method=''):
+    def wrap1(f):
+        def wrap(*args, **kwargs):
+            t = time.time()
+            res = f(*args, **kwargs)
+            ref = 365.8015799324624
+            cost = -list(res)[0]
+            duration = time.time() - t
+            print("%s improved AEP to %f.4fGWh (%+.4f%%) in %.3fs" % (name, cost, (cost - ref) / ref * 100, duration))
+            url = "http://tools.windenergy.dtu.dk/topfarm_ex/insert_result.asp"
+            values = {'user': name,
+                      'time': duration,
+                      'aep': cost,
+                      'comment': method,
+                      }
+            data = urlencode(values).encode("utf-8")
+            req = Request(url, data)
+            urlopen(req)
+            return res
+        return wrap
+    return wrap1
+
+
+def plot_result():
+    url = "http://tools.windenergy.dtu.dk/topfarm_ex/view_result.asp"
+    req = Request(url)
+    s = urlopen(req).read().decode()
+    res_dict = defaultdict(list)
+    for r in s.split("<br>")[:-1]:
+        name, duration, aep, comment = r.split(";")
+        res_dict[name].append((duration, aep, comment))
+    fig = plt.figure(figsize=(25, 10))
+    ref_aep = 365.8015799324624
+    duration_lst = []
+    for i, name in enumerate(sorted(res_dict.keys())):
+        duration = np.array([res[0] for res in res_dict[name]], dtype=np.float)
+        duration_lst.extend(duration)
+        aep = np.array([res[1] for res in res_dict[name]], dtype=np.float)
+        marker = "v^<>.ospP*X"[i // 10]
+        plt.plot(duration, (aep - ref_aep) / ref_aep * 100, '^', label=name, marker=marker)
+    plt.plot([min(duration_lst), max(duration_lst)], [0, 0], 'gray')
+    best = (418.9244064 - ref_aep) / ref_aep * 100
+    plt.plot([min(duration_lst), max(duration_lst)], [best, best], 'gray')
+    plt.xlabel('Time [s]')
+    plt.ylabel('AEP improvement [%]')
+    plt.legend()
+    return fig
+
+
+def reset_results():
+    url = "http://tools.windenergy.dtu.dk/topfarm_ex/reset_results.asp"
+    req = Request(url)
+    urlopen(req)
+
+
+if __name__ == '__main__':
+    fig = plot_result()
+    plt.show()