Getting the transcript
Reading the captions from YouTube. A video nobody has opened here before takes 10 to 30 seconds; this page fills in on its own.
Getting the transcript
Reading the captions from YouTube. A video nobody has opened here before takes 10 to 30 seconds; this page fills in on its own.

Sahas Pokhrel · @Sahas_Project_Management
Words
674
Runtime
4:35
Speaking pace
147wpm
Reading time
3min
147 words per minute, below the 160 25th percentile of 349 measured videos. That distribution comes from the 349-video hook study.
Opening (first 30 seconds)
Lately, AI is screening a resume before a hiring manager ever sees it. Now, is your resume passing that test? If not, don't worry, we'll upgrade it in just a few clicks. And also based on Jeff's research benchmark. So let's get started. Great. First, let's install the killer resume as an extension in your browser. Please find the link in the description section below. Now with that done, the moment you click the
74 words, the words spoken in the first 30 seconds at 147 words per minute.
Free, no signup. See how the first 30 seconds hold attention, with rewrites.
Sentence shape
| Measure | This transcript |
|---|---|
| Sentences | 53 |
| Average words per sentence | 12.7 |
| Longest sentence | 44 words |
| Questions asked | 3 |
| Sentences containing a number | 0 |
Most used terms
Filler phrases
11 in total: actually 7 · like 2 · right? 2.
A literal whole-word count of the same phrase list the Prepublish browser extension uses, so a phrase inside another word is not counted and a phrase used in its ordinary sense still is. It is a count and not a judgement.
Run the check on the words above: where attention is likely to drop, with a rewrite for each weak line. The free check shows the scores and the one issue costing the most.
What this transcript is
Every word below is the caption track YouTube publishes for this video, pulled from the video itself and reproduced unchanged. It is not Prepublish's writing, not a summary, and not a re-transcription: it is the video's own published captions. English captions, published by the channel, in the video’s original language. Source: the video on YouTube. A channel that would rather this page did not exist can ask for its removal through the contact page, and it is removed.
No Script X-ray for this video: YouTube shows a Most replayed graph only once a video has enough views.
Lately, AI is screening a resume before a hiring manager ever sees it. Now, is your resume passing that test? If not, don't worry, we'll upgrade it in just a few clicks. And also based on Jeff's research benchmark. So let's get started. Great. First, let's install the killer resume as an extension in your browser. Please find the link in the description section below. Now with that done, the moment you click the icon in the toolbar, it opens as a full workplace right in your browser.
And here's the best part. You can also deploy your agents. And if not, it has a built in offline engine that runs privately on your machine anyway. But for better results, I always recommend connecting it to an agent API as it adds one more layer of intelligence while optimizing your resume. And for this demo, I am connecting it to visceral, which is currently giving a free API access to me, and I would recommend you doing so.
Great job. Now let's give it a job to work with. I'll first paste in a program manager job description from Google Careers. Now this gives the agent the proper context it needs to understand what the company is actually looking for. Now with that, I moved to Second Step where I upload my current resume. Now see, as soon as it's uploaded, now the agent runs a quick idiot check. And this is the very first thing Jeff talks about making sure the AI can actually read your resume.
It's just like asking if the applicant tracking system actually reads the document properly or not. Now let's quickly run the health check. Amazing. My resume scored area over two hundred now, which is pretty good. But still, there's a clear room for improvement. Now the agent is showing me what's working and where the gaps are. Now, this is also where we'll look at another one of Jeff's point. Making your feet Obvious.
Now, see, I could let AI optimize everything immediately, but I do not recommend this step right away because I want my agent to work on my real achievement, rather than just fabricating information from the internet, which would not be valid for me. Okay. Now here I select my job roles and add my achievement specific to the job that I did. Now see here, there are already some pre-populated tags to which is making this work very easier and I can just update them, edit them based on my actual experience, right?
And this is important because Jvzoo makes a very similar point, saying that we should know where AI should actually stop as well. And I am not letting AI to make up my achievements. I'm also trying to prove my job achievements with numbers. That stands with Jeff's fourth rule. And the agent here follows the XYZ structure. And finally, Jeff's fifth rule proving your skills. Now, simply writing ChatGPT or prompt engineering on your resume does not tell a recruiter much.
So instead I can connect the AI tools I've actually used to real workflows and outcomes. That would be a much stronger evidence than just listing a tool, right? Amazing. Now I'll just simply let the agent put everything together and we are done. My resume went from eighty points to ninety eight based on the agent scoring model measured against Jeff's benchmark. Now see, what's important is that I can actually see what changed here.
My resume is definitely looking better based on the job description. My achievements are looking more miserable now, and the AI skills now have real evidence behind them. Now I can review everything before I actually use the resume. Thank you so much for watching this long. If this video helped you, please drop a like in this video. And I do talk about product and project management. So if either of this interests you, please subscribe to my channel and I'll wait to see you in my next video.
The words are the caption track's own and nothing is reworded or re-transcribed. Paragraph breaks are placed between sentences so the text reads as prose.
Free tools for your own script: paste a draft and see where it stands before you record it.
Paste your draft and see where viewers are likely to drop off, with a rewrite for each weak line.
Paste the first 30 seconds of your own draft for a hook score and rewrites.
Check your draft against YouTube's advertiser-friendly guidelines before you record it.
Read this channel's public videos and transcripts, and download a writing brief for it.