Power systems are facing grand challenges from increasing dynamics and stochastics from both the generation and the demand sides. This has caused great difficulty in designing and implementing optimal control for the grid in real time. Tremendous efforts have been spent in the past on computational methods and advanced modeling techniques that provide faster and better situational awareness, based on measurements from advanced grid sensors, PMU as an example. However, as grid operators are heavily involved in the decision-making process, the entire procedure has not been made fully automated, limiting the potential of such applications. That is, not only does the 'grid' need to perceive faster, it also needs to think and act faster. Towards this end, sub-second autonomous control schemes need to be developed. Over the past years, the PMU & System Analytics Group at GEIRI North America has built up an autonomous grid dispatch and control platform using deep reinforcement learning, the Grid Mind. Combined with Grid Eye, the grid monitoring and situational awareness platform, Grid Mind has demonstrated promise in helping address the pressing issues modern power systems faces. This talk will summarize this developmental effort while focusing on the key technologies utilized for the Grid Mind framework.