Reverse-engineer a creator's style: an AI persona and style guide from their latest videos
Disclosure: I build TubeText . This post uses our Video Breakdown AI Actor on Apify. The output below is from a run I did today. When you study a creator, the useful question isn't "what is this video about?" but "what does this person do every time?": which hooks they open with, how fast they cut, what they sell, how they end. Answering that means watching a dozen videos with a notepad. Here's…
In the latest videos, Marques Brownlee, also known as MKBHD, employs certain patterns and techniques consistently that can be identified to create an AI persona and style guide. Using the Video Breakdown AI Actor, the analysis was performed on his 5 most recent Shorts. The output provides a summary row containing key statistics and insights.
The summary reveals that MKBHD's videos typically last around 66 seconds, with about 10 cuts per minute and 11 shots in each video. The content primarily focuses on product reviews and deep dives, accounting for 60% of his content. The second most prominent category is tech industry news and analysis, making up 20% of his videos, while concept and speculative tech content also account for 20%.
The analysis also identifies two main hook patterns used by MKBHD. Three of his most recent Shorts start with a visual surprise, while two begin with a bold spoken claim. These hooks are delivered as voice over and work to grab the viewer's attention. Additionally, the persona, tone, and voice of MKBHD's videos are characterized as friendly, informative, and trustworthy.
On-screen text is kept to a minimum, used only for critical data points or emphasis. The suggested style guide offers seven rules, three of which are:
1. Begin with an immediate visual or auditory hook that defies expectations.
2. Prioritize "show, don't tell" by using high-quality B-roll to demonstrate features.
3. Keep on-screen text minimal, using it only for critical data points or emphasis.
Comparing these insights to other competitors can help in understanding the effectiveness of MKBHD's style. Moreover, the per-video rows allow for checking the summary against actual evidence, ensuring accuracy. Each of MKBHD's 5 videos has its own row, detailing the type of hook used, delivery method, and why it works effectively.
In summary, this analysis provides a concise overview of MKBHD's latest video style, with concrete data points that can be used to craft an AI persona and style guide. While this run used 5 Shorts as a sample, more data points (around 10-20 videos) would yield more accurate results. The account summary row is free while in beta, and the analysis costs only about $0.15 for this sample.
Written by urgent.news from Dev.to's reporting — not their text. Machine-written — may contain errors; check the original before relying on it.
