Aspects of the technology described herein allow a user to add tags to a video as the video is being recorded. The tags can be added by capturing the user's voice as the video is recorded. Aspects can be performed by a head-mounted display. The head-mounted display can include an augmented reality display. In one aspect, a list of tags are displayed. The tags can be selected from a curated list of tags associated with a project the user is filming. For example, a project could comprise a building inspection during construction. In another aspect, the most commonly used tags in a given context can be shown. The most commonly used tags associated with a particular context can be determined through machine learning process. At a high level, a machine learning process can sort through historical tag data and associated contexts to determine a pattern correlating a context to a tag.