Use your existing TikTok video library and their associated comment threads to generate highly relevant new content ideas and scripts. This workflow pairs audience feedback directly with the specific video performance that prompted it, leading to targeted and engaging new topics.
with Claire Vo
I am logged in and use the video in the Google Drive like you did before so that you can read the comments And use those comments to, uh, put together new content ideas based on what they said.
A list of new video ideas or draft scripts that directly address questions and topics raised by your audience in the comments of a specific video.
Anthropic AI assistant
Google Drive stores and shares files, including the source video library used in this workflow.
Google Chrome is a web browser, used here to access an authenticated TikTok session.
Follow the sequence once, then adapt the prompts, checks, and handoffs to your own setup.
4 steps
Because direct scraping of TikTok is unreliable, manually download your published videos from the app and upload them to a dedicated folder in Google Drive. This creates a stable content library for the AI to access.
This human-in-the-loop step is crucial for reliability. Don't build a system that depends entirely on unattended access to a third-party platform.
With your videos in Google Drive and a logged-in TikTok session open in your browser, prompt Claude to connect the two sources of information for a specific post.
Access the video named `[video_file_name.mp4]` from my Google Drive. Now, using my logged-in browser, navigate to the TikTok post at `[URL_of_TikTok_post]` and read its comment thread. Synthesize the video's content and the comments to propose three new content ideas.
This process was confirmed in the transcript: pair the video's content with its comments, then use that combination to propose new material [20:42].
Go beyond the text by directing the AI to analyze specific aspects of your delivery in the source video. This helps it understand what makes your style unique.
In that video, notice the hook where I say, 'I've been in tech for 25 years...' and give a little laugh. Analyze the cadence and tone. When you generate new scripts, write a hook that uses a similar pattern of a bold statement followed by a moment of levity.
This is far more effective than a vague instruction like 'write in my voice.' Point to a specific, observable moment in your performance and explain its function.
Evaluate the list of ideas and scripts generated by Claude. The AI's role is to surface opportunities from audience feedback; your role is to decide which ones are worth pursuing.
Prioritize ideas that answer direct questions from your audience, as seen with the example about AI for hospital billing [21:08]. These topics have a pre-validated interest.
Turn an idea into a PRD, user stories, and a plan.
How to recover when the loop fails and where human judgment helps.
Let routine work keep moving.
A step-by-step guide to signing up for Meta's Muse API, installing the Muse Code command-line tool, and running it headlessly with an external agent like Claude Code for easier testing and benchmarking.
Benchmark an agentic AI model's ability to resolve complex customer billing issues. This workflow tests the AI's ability to investigate tickets, handle complex logic, execute changes in an admin app, and communicate with the customer.
Adapt Brooke Lacey’s Claude Code workflow to edit phone footage with FFmpeg, Whisper, and Python. Use a TSV cut list to review timing, then render a vertical video with captions and graphics.
Join 250,000+ product managers who use ChatPRD to write better docs, align teams faster, and build products users love.
