At a high level, TacTex operates by making predictions or estimates concerning various factors (such as unknown game parameters, user populations, and competitor bids) and then by finding the optimal actions given this information. These tasks are divided among a number of modules,as depicted in the figure above.

At the start of each new day, the game server sends TacTex a report on the results of the previous day. The first module to be called is the Position Analyzer, a preprocessor that converts some of this information into a more useful format.

TacTex then performs all necessary prediction and estimation using three modules. The User Model uses the total number of queries for each query type to estimate the composition of the different user populations. From these estimates, predictions about future user populations can be made. The Advertiser Model takes information relating to the actions of other advertisers and predicts the actions these advertisers will take in the future. The Parameter Model maintains estimates of unknown game parameters by finding those parameters that best fit the known auction outcomes.

Finally, TacTex must use these predictions and estimates to choose the optimal bids, ads, and spending limits to submit to the game server for the next day. The Query Analyzer uses the information received to compute the expected outcomes of actions, such as how many clicks and conversions would occur for a given query type. The Multi-day Optimizer is responsible for dividing available capacity among the remainder of the game days, and it calls the Single-day Optimizer to divide each day's capacity among query types using the information provided by the Query Analyzer.

A complete agent description can be found in the papers section.