In the classic children's game of Hangman, a player's objective is to identify a hidden word of which only the number of letters is originally revealed. In each round, the player guesses a letter of the alphabet: if it's present in the word, all instances are revealed; otherwise one of the hangman's body parts is drawn in on a gibbet. The game ends in a win if the word is entirely revealed by correct guesses, and ends in loss if the hangman's body is completely revealed instead. To assist the player, a visible record of all guessed letters is typically maintained.For this project, we trained a neural network to play Hangman by appropriately guessing letters in a partially or fully obscured word. The network receives as input a representation of the word (total number of characters, the identity of any revealed letters) as well as a list of which letters have been guessed so far. It returns a guess for the letter that should be picked next. This repo shows our method for training the network with Microsoft's Cognitive Toolkit (CNTK) and validating its performance on a withheld test set, as well as operationalizing the model for gameplay on an Azure Web App.