Margareth Felicia Gono, 24, recently started as a senior associate at DoorDash after completing a master’s degree in applied analytics in May. During her job search, she created an AI workflow that helped her evaluate roles and analyze interview sentiment. The following is based on conversations that have been edited for brevity and clarity.
At the beginning of my job search, it was pretty scattershot. Because I was an international student and needed a visa, I felt I had to apply to anything that might relate to my experience, even if it wasn’t the right fit.
I grew up in Indonesia and didn’t want to leave the US without getting corporate experience. My parents paid for my tuition at a private university, then an Ivy League master’s on top of that.
I started tracking my results. What roles got responses? What didn’t? What patterns showed up? Anxiety is unprocessed data. I was tired of feeling bad about my search and figured I might as well learn something instead.
Around the second or third round of interviews, I noticed I would get a little bit of hesitation from employers, and I wanted to understand why that was happening. Was it me, my experience, my résumé, or that I needed a visa?
I used Claude as a career coach
I used Claude almost like a partner and built this tracker for my applications. I’d take a job description and ask Claude to identify the main skills, keywords, and themes. Then I built another automation agent into that same project. Basically, it was my own version of what people call an ATS score. I’d paste the job description and my résumé together and ask, “What top keywords am I missing?”
I didn’t want AI to invent experience or make me sound like everyone else. I wanted it to show me where my experience wasn’t being communicated clearly enough. Sometimes that meant changing one bullet. Sometimes it meant realizing that applying would be a waste of time.
As I went along, I became more intentional about who I wanted to work under and what types of jobs I applied for. I used Claude to act like a career coach and figured out I liked three things: talking to people, making things pretty, and finding patterns. As a result, I made three résumés: one for analytics, one for sales and marketing, and one for consulting.
Eventually, I used Claude to turn that into a simple dashboard, so I could see what was happening: 186 applications, 44 cold outreaches, 19 interviews, six take-home assignments, three final rounds, and one offer. Seeing it that way made the process feel less like 185 personal failures, and more like a funnel I could keep improving.
I treated an interview like a conversation
During the process, I started treating every interview like a real conversation instead of an audition. I also really wanted to find someone who was not just a good boss but also a good mentor.
When recruiters said they were using an AI note-taker, I’d ask if I could record, too. Most said no. With the yeses, I would scrape the notes and use a sentiment analysis to figure out where I hesitated or used filler words, where the interviewer asked me to get more specific, where they seemed engaged, agreed, or laughed. Even when I couldn’t record, I’d write down what I remembered right after — what they asked, where I rambled, what seemed to interest them.
I also used AI to research the people I was interviewing with. I built a skill in Claude to scrape LinkedIn profiles. I copy and paste everything on their page, and by now, Claude knows who I am because I talk to it a lot. So I ask it to find similarities to me. In one case, I connected with a recruiter over a cheese club we’d both been part of, years apart. That got me further than any cover letter or résumé font choice ever did.
I also think the questions at the end of an interview can make or break it. I would ask how they got to where they are, and what advice they’d give someone just graduating. I think when you stop letting the interviewer drive the entire conversation and actually engage back, you go further.
It’s easy to have imposter syndrome, but I tried to remember that this is a process, and I know my experience. I’ve done my research. I know why I want to apply to this job, and if they don’t see my value, someone else will.
Everyone has access to AI now, so that isn’t a differentiator. What makes the difference is knowing what to ask, how to interpret what AI gives you, and where judgment still matters. AI can help you see patterns, but you have to decide what they mean. It can help you get your foot in the door, but it can’t make you want the job or make someone remember you.
Do you have a story to share about your job search? Contact this reporter at tparadis@businessinsider.com.
