I built one honest profile document and had Claude play a hard-to-please recruiter before interviews
I'm early in my career, in marketing and communications, and every interview circles back to the same four questions: tell me about yourself, why this role, what are your weaknesses, where do you see yourself in five years. A generic answer to those is always sitting right there, ready to say, and it always sounds exactly like what it is. What isn't sitting there ready is an answer built out of my actual history, delivered in a voice that sounds rehearsed a few times over rather than read off a script.
So before a round of interviews I sat down once and wrote a single long document about myself: my education, each past role described as what actually happened rather than as a pile of adjectives, the specific skills and tools I use, a section on how I want to sound in an interview (professional, natural, concrete — explicitly not stiff or over-rehearsed), and a section naming where I'm genuinely weaker. I wrote that section as plainly and specifically as I could. A vague weakness gets a vague answer back — the more real the constraint, the more the AI actually has to work with instead of writing generic confidence around me.
Then, before each interview, I paste that document into Claude or ChatGPT along with the actual job posting and give one explicit instruction: play a demanding recruiter for this specific role, ask realistic questions including the hard and skeptical ones, and when critiquing my answers, push back on anything generic or anything the document doesn't actually support. I ask it to be hard to please, not encouraging.
What comes out is tailored answers to the standard set, anchored in real facts instead of a generic template, plus a live simulation I can run out loud before I'm ever in front of an actual recruiter. The steps I follow and the exact instruction I paste in are below, along with the three places this still isn't enough on its own.
Steps
- 1
Write the profile document once, honestly
Cover education, each past role described concretely (what you actually did, not adjective piles), the specific skills and tools you use, how you want to sound in an interview, and a plain section naming where you're genuinely weaker. That last section is what stops the AI from writing generic confidence around you — it has real constraints to work with instead.
- 2
Paste it in together with the actual job posting
Before each interview, paste the document plus the real listing into Claude or ChatGPT in the same message. The posting is what keeps the practice questions specific to that role instead of generic interview-prep filler.
- 3
Give the explicit 'hard recruiter' instruction
Tell it directly to play a demanding recruiter for this role, ask the standard questions plus the harder skeptical ones, and push back on anything in your answers that's generic or not backed by the document. Ask for hard to please, not encouraging.
- 4
Work through the standard four and rewrite what drifts
Tell me about yourself, why this role, your weaknesses, five years from now — let it critique each answer, and rewrite until every claim traces back to something specific in the document rather than a phrase that could apply to anyone.
- 5
Run it as a spoken back-and-forth, not a reading exercise
Answer the simulated questions out loud instead of just reading the finished text. That's the only part of this that tests whether you can actually say the words under pressure, not just write them well.
PART 1 — Interview profile document (fill this in once, before your first interview)
# Interview Profile — [Your name]
## Education
[Degree(s), school, year — the actual facts, not "strong academic background"]
## Work history
For each past role, write it as what happened, not as adjectives:
- Company / title / dates
- What I actually did — concrete tasks and situations ("built X," "ran Y," "handled Z"), no "results-driven," no "dynamic team player"
## Skills and tools
[The specific tools and skills you actually use day to day, named — not summarized as a vague competency]
## How I want to sound
Professional, natural, concrete. Not stiff, not over-rehearsed, not like I'm reading from a script.
## Where I'm genuinely weaker
[Name your real gaps honestly and specifically. The more concrete this section is, the more the AI has to work with real constraints instead of writing generic reassurance around them — a vague weakness gets a vague, useless answer back.]
---
PART 2 — Recruiter simulation prompt (paste this after the document above, plus the job posting)
Here is my interview profile document, and below it the job posting for the role I'm interviewing for.
[PASTE THE JOB POSTING HERE]
I want you to play a demanding recruiter interviewing me for this specific role. Ask realistic interview questions, including the standard ones (tell me about yourself, why this role, what are your weaknesses, where do you see yourself in five years) and the harder, more skeptical ones a real recruiter would ask given this posting and my background.
After each answer I give, critique it. Push back specifically on anything that sounds generic or that isn't actually supported by my profile document. Don't be encouraging — be hard to please. If an answer could apply to any candidate, tell me so and make me redo it using something specific from the document.Where this breaks
Left unchecked, the AI drifts toward a confident, slightly inflated "LinkedIn voice" within a few exchanges — it will round "familiar with AI tools" up to "AI expert" if you let it, so every finished answer needs a pass where I personally check it isn't overclaiming past what the profile document actually supports. Reading a good written answer back is not the same skill as saying it out loud under pressure: the document gets the content right, but I still have to rehearse it out loud, ideally against the simulated questions, or the real interview is the first time I've ever said the words. And the document goes stale after every actual interview — new questions come up that I hadn't anticipated, and if I don't go back and add them into the document afterward, the next prep session starts from the same gaps as the last one.
Did this work for you?
Sign in to report a result. This is the number everyone reads first.