Summarize a YouTuber's latest video into a Google Doc daily
Discover how to build AI agents with Make.com to automate complex tasks without coding. Task: Discover how to build AI agents with Make.com to automate complex tasks without coding. This guide walks you through setting up goal-oriented agents that leverage large language models, integrate with various apps, and adapt in real-time to streamline your business processes. Alright, so keeping up with specific YouTube channels can take time. For example, I really like following Matthew Berman's content (@matthew_berman), but manually watching every video, grabbing the key points, and saving them somewhere is a chore. I thought, "There has to be an automated way!" – especially since I wanted a summary of his latest video title and description put into a Google Document for me every morning at 9 AM. I decided to build this automation using Make.com, known for its visual workflow builder. Here’s a detailed look at how I set up my Make scenario to handle this task automatically. How I Built the Workflow in Make make ai agent My setup in Make uses a sequence of connected blocks, which they call modules. Each module does one specific job, passing information to the next one. It looks like this: Schedule: Starts everything at the right time. YouTube: Finds the latest video. Hugging Face: Creates the AI summary. Google Docs (Create/Find): Gets the document ready. Google Docs (Append): Adds the summary to the document. Let's break down what each step (module) does: Breaking Down the Steps (Modules) YouTube Module (Finding the Video): What it does: This is my starting point for getting the content. I configured this module to specifically search YouTube for the channel handle @matthew_berman and grab the details of his most recent video. What info it gets: It pulls out the video's Title and Description. How I set it up: I needed to connect my Google/YouTube account to Make so it had permission to search YouTube using its official API. Hugging Face Module (Summarizing with AI): What it does: This module takes the Title and Description text passed from the YouTube module and feeds it to an AI model designed for summarizing text. Its job is to create a shorter, concise version of the video's main points. Which AI Model? Make often uses powerful pre-trained models available through Hugging Face. For summarization, it likely uses a model like Facebook's BART (specifically facebook/bart-large-cnn), which is excellent at this task. Settings: I could adjust settings here, like telling it the maximum or minimum length I wanted the summary to be, ensuring it's brief and useful. How I set it up: This was important – I had to create a Connection within Make to Hugging Face. This usually involves signing into my Hugging Face account (or creating one) and allowing Make to use its API services for summarization. First Google Docs Module (Creating/Finding the Doc): What it does: Before adding the summary, I needed a place to put it. This module either creates a brand new Google Document each day or finds a specific existing one I want to keep adding to. Settings: I could set it up to name the new document automatically, maybe using today's date or the video title. Or, I could point it to a single "Matthew Berman Summaries" document. I could even have it use a Google Docs template if I wanted specific formatting. How I set it up: Just like YouTube, I needed to connect my Google account and give Make permission to create or edit documents in my Google Drive. Second Google Docs Module (Adding the Content): What it does: This final module takes the summarized text from the Hugging Face module and neatly inserts it into the Google Document prepared by the previous step. Formatting: I set this up to structure the entry clearly, perhaps including the original Video Title, maybe a Link back to the video (if the YouTube module provided it), and then the AI-generated Summary. Keeping Records: By having this module append text (add to the end), my Google Doc becomes a running log of daily video summaries. Making It Run Daily (Scheduling) The Trigger: The whole process starts automatically because the very first block isn't one of the action modules – it's Make.com's built-in Scheduler. How I set it up: I went into the scenario's scheduling settings. I configured it to run every day specifically at 9:00 AM. Make allows setting precise times like this (sometimes using time windows like 9:00 AM to 9:05 AM to ensure it runs). I could even tell it to skip weekends if I wanted. Setting It Up (The Important Connections!); tools: Make. Human role: The original post does not say how a person stayed involved.; limitations: Requires valid API connections for YouTube, Hugging Face, and Google Docs. The source mentions using facebook/bart-large-cnn for summarization but does not specify costs or rate limits. Human intervention is needed for initial setup and ongoing monitoring of API permissions. The source does not detail exception handling for missing videos or API failures..
Tools
Published on Agent Work Atlas:
Overview
Discover how to build AI agents with Make.com to automate complex tasks without coding.
Workflow
Discover how to build AI agents with Make.com to automate complex tasks without coding. This guide walks you through setting up goal-oriented agents that leverage large language models, integrate with various apps, and adapt in real-time to streamline your business processes. Alright, so keeping up with specific YouTube channels can take time. For example, I really like following Matthew Berman's content (@matthew_berman), but manually watching every video, grabbing the key points, and saving them somewhere is a chore. I thought, "There has to be an automated way!" – especially since I wanted a summary of his latest video title and description put into a Google Document for me every morning at 9 AM. I decided to build this automation using Make.com, known for its visual workflow builder. Here’s a detailed look at how I set up my Make scenario to handle this task automatically. How I Built the Workflow in Make make ai agent My setup in Make uses a sequence of connected blocks, which they call modules. Each module does one specific job, passing information to the next one. It looks like this: Schedule: Starts everything at the right time. YouTube: Finds the latest video. Hugging Face: Creates the AI summary. Google Docs (Create/Find): Gets the document ready. Google Docs (Append): Adds the summary to the document. Let's break down what each step (module) does: Breaking Down the Steps (Modules) YouTube Module (Finding the Video): What it does: This is my starting point for getting the content. I configured this module to specifically search YouTube for the channel handle @matthew_berman and grab the details of his most recent video. What info it gets: It pulls out the video's Title and Description. How I set it up: I needed to connect my Google/YouTube account to Make so it had permission to search YouTube using its official API. Hugging Face Module (Summarizing with AI): What it does: This module takes the Title and Description text passed from the YouTube module and feeds it to an AI model designed for summarizing text. Its job is to create a shorter, concise version of the video's main points. Which AI Model? Make often uses powerful pre-trained models available through Hugging Face. For summarization, it likely uses a model like Facebook's BART (specifically facebook/bart-large-cnn), which is excellent at this task. Settings: I could adjust settings here, like telling it the maximum or minimum length I wanted the summary to be, ensuring it's brief and useful. How I set it up: This was important – I had to create a Connection within Make to Hugging Face. This usually involves signing into my Hugging Face account (or creating one) and allowing Make to use its API services for summarization. First Google Docs Module (Creating/Finding the Doc): What it does: Before adding the summary, I needed a place to put it. This module either creates a brand new Google Document each day or finds a specific existing one I want to keep adding to. Settings: I could set it up to name the new document automatically, maybe using today's date or the video title. Or, I could point it to a single "Matthew Berman Summaries" document. I could even have it use a Google Docs template if I wanted specific formatting. How I set it up: Just like YouTube, I needed to connect my Google account and give Make permission to create or edit documents in my Google Drive. Second Google Docs Module (Adding the Content): What it does: This final module takes the summarized text from the Hugging Face module and neatly inserts it into the Google Document prepared by the previous step. Formatting: I set this up to structure the entry clearly, perhaps including the original Video Title, maybe a Link back to the video (if the YouTube module provided it), and then the AI-generated Summary. Keeping Records: By having this module append text (add to the end), my Google Doc becomes a running log of daily video summaries. Making It Run Daily (Scheduling) The Trigger: The whole process starts automatically because the very first block isn't one of the action modules – it's Make.com's built-in Scheduler. How I set it up: I went into the scenario's scheduling settings. I configured it to run every day specifically at 9:00 AM. Make allows setting precise times like this (sometimes using time windows like 9:00 AM to 9:05 AM to ensure it runs). I could even tell it to skip weekends if I wanted. Setting It Up (The Important Connections!)
Reported result
The source describes the intended outcome of saving time on manual content tracking but does not provide measured metrics or confirm successful execution logs. It states the workflow automates the task of checking YouTube and creating documents. No specific data on error rates or actual time saved is reported.
Human role
The original post does not say how a person stayed involved.
Limitations
Requires valid API connections for YouTube, Hugging Face, and Google Docs. The source mentions using facebook/bart-large-cnn for summarization but does not specify costs or rate limits. Human intervention is needed for initial setup and ongoing monitoring of API permissions. The source does not detail exception handling for missing videos or API failures.
Try it
I want to automate daily summaries of a specific YouTube channel into a Google Doc using Make.com. My channel handle is [replaceable_channel_handle]. I need the summary of the latest video's title and description appended to a Google Doc named [replaceable_doc_name] every day at [replaceable_time]. Steps: 1. Create a Make scenario with a Scheduler trigger set to [replaceable_time]. 2. Add a YouTube module to search for the latest video from [replaceable_channel_handle] and extract Title and Description. 3. Add a Hugging Face module using a summarization model (e.g., facebook/bart-large-cnn) to process the text. 4. Add a Google Docs module to find or create [replaceable_doc_name]. 5. Add a second Google Docs module to append the summary, video title, and link to the document. Before enabling the schedule, run a single manual test with a sample video. Show me the output in the Google Doc for my approval. If the summary is poor or the API fails, stop and ask for clarification on the model or channel. Do not enable the daily schedule until I confirm the test result is acceptable.
Source reports are not independently verified. Publication date is the catalog publication date, not the original article date.