“Why us?” trips most candidates because the safe answer (mission, culture) is also the one every other applicant gives. The fix is mechanical, not magic: name one real thing the company did, and map it to one real thing you have done. AI can phrase that connection well, but it cannot supply the facts. So the work splits cleanly. You do 15 minutes of research; the prompt turns your notes into a tight, honest answer.
The 2026 reality: vague answers read as AI
A large share of candidates now use AI somewhere in their application, and recruiters have stopped pretending otherwise. Greenhouse’s public stance is that AI assistance on a resume or cover letter is fine, as long as the materials still represent your real qualifications. Standard applicant tracking systems score how well you match the role; they generally do not flag who wrote the text. So the risk is not “you got caught using AI.” The risk is blandness.
Recruiters report two reliable tells. First, generic phrasing: lines like “proven track record,” “industry-leading,” and “I’m passionate about your mission” appear in millions of AI drafts, so yours blends into the pile. Second, and far more damaging, the interview mismatch: the candidate cannot explain, in their own words, the claims their cover letter made. Every prompt below is built to defeat both: force specifics in, keep the wording yours, and never let the model invent a fact you cannot defend out loud.
Who this is for
Candidates prepping a “why us / why this team” answer, career switchers tying a pivot to a target company, and anyone who has given the same generic answer to five different employers.
Do the 15-minute research pass first
The prompts below are useless without raw material. Spend 15 minutes collecting concrete signals, then feed them in. Where to look:
| Source | What to grab | Why it lands |
|---|---|---|
| Engineering / product blog | A recent shipped feature, a postmortem, a design decision | Shows you read past the homepage |
| Latest funding or earnings note | Stage (Series B to C, post-IPO), a stated priority | Frames your “why now” |
| The job description itself | The actual problems the role owns | Ties you to the work, not the brand |
| A team member’s talk, LinkedIn post, or conference deck | A specific opinion or project they own | Powers “why this team” |
| Glassdoor / Blind (read skeptically) | A culture pattern, repeated praise or gripe | Surfaces honest hesitations to address |
Paste these notes verbatim into the prompts. The quality of the answer is capped by the quality of your notes, not the model.
Prompt anatomy
Every “Why this company” prompt should carry six elements:
- Role: candidate, hiring manager, or recruiter; name who the model plays.
- Context: target role, company, level, your background.
- Goal: one deliverable (spoken answer, cover-letter paragraph, recruiter reply).
- Constraints: word count, banned phrases, must-include facts.
- Tone: pick 2-3 anchors (confident, curious, measured).
- Examples: paste 1-2 of your past answers so the model copies your voice, not its own.
Which model to use (June 2026)
Any current frontier model handles this well; the differences are small at this task. Claude Sonnet 4.6 (free tier, or Pro at $20/mo) and ChatGPT GPT-5.5 (Free, or Plus at $20/mo) both write natural spoken-answer cadence. Gemini 3.1 Pro (Google AI Pro, $19.99/mo) is convenient if your research lives in Google Docs. None of them can browse your private notes, so paste your research in. For the strongest “does this sound like me” match, give the model 1-2 real writing samples and tell it to mirror sentence length and word choice.
12 copy-ready prompt templates
The templates use [bracketed] placeholders. Swap them for your real notes before running.
1. Three-prong answer
Company: [company]. Role: [role]. My background: [me].
Write a 90-second spoken "Why this company" answer with 3 prongs:
(a) a specific thing about the company's work I can name,
(b) a specific thing about this role that fits me,
(c) a relevant connection from my past.
No mission praise. Plain spoken English, my voice.Swap: company, role, me
2. Specific product / decision callout
From these notes about [company]: [paste research],
pull the 3 most concrete signals (a shipped feature, a launch, a public retro).
For each: what it tells me about how they work, and how I connect to it.
Flag any signal I should verify before saying it out loud.Swap: company, paste research
3. Why-not version
Articulate what is NOT my reason for wanting [company]:
not the stock, not the brand, not because I'm unhappy now.
Then state what IS the reason, in one tight paragraph.
The contrast filters out generic answers.Swap: company
4. Map company values to your past
[company] says they value [values].
For each value, find one real experience of mine that demonstrates it,
using only this background: [me].
Do not invent anything; flag any value I have no story for.Swap: company, values, me
5. Why now
Why [company] NOW, vs. 2 years ago or 2 years from now?
Tie the timing to (a) where the company is on its arc
(Series B to C, post-IPO, post-pivot): [stage],
and (b) where I am on mine: [my stage]. One paragraph.Swap: company, stage, my stage
6. Why this team specifically
Within [company], why this team [team]?
Cite a specific signal from my notes: [paste signal]
(a hiring page, a public deck, a team member's talk or blog).
Avoid "I want to work with smart people."Swap: company, team, paste signal
7. Strip the pandering
Audit this draft for pandering:
[paste draft].
Flag phrases like "impressive growth," "industry-leading,"
"passionate team," "love what you stand for."
Replace each with a specific, checkable observation.Swap: paste draft
8. Cover-letter Why-us paragraph
Compress this 90-second answer into a 4-sentence cover-letter paragraph:
[paste answer].
Tone: confident, not breathless. Skip "I was excited when..."
and any line that could apply to a different company.Swap: paste answer
9. Career-switcher Why-this-company
I'm switching from [from] to [to].
Tie my pivot to why [company] is the right place for it:
a project that maps to my old field, a values fit,
or a role built for switchers. Use only this background: [me].Swap: from, to, company, me
10. Late-round Why-us refresh
I'm in round 4 and gave the "Why us" answer in round 1.
Refresh it: name what I learned in earlier rounds that
strengthened the fit: [paste notes],
plus one open question this interview can help me answer.Swap: paste notes
11. Honest hesitation
I have one real hesitation about [company]: [hesitation].
Write an answer that names the trade-off honestly
without sabotaging my candidacy, and explains why the
upside still outweighs it. No spin.Swap: company, hesitation
12. Anti-cliche vocabulary swap
Banned words in this draft: passionate, excited, thrilled,
honored, dream, perfect, leading, impactful.
[paste draft].
Rewrite using specific verbs and concrete observations instead.Swap: paste draft
Pressure-test before the interview
The biggest tell is the interview mismatch, so rehearse the answer against follow-ups. Use the model as a hostile panelist:
Here is my "Why this company" answer: [paste answer].
Play a skeptical interviewer. Ask me the 3 sharpest follow-up
questions that would expose a candidate who hadn't done real research.If a follow-up stumps you, that line is not yours yet. Go back to your notes or cut the claim.
Common mistakes
- Treating AI output as the final answer; the cadence is detectable and the claims become yours to defend.
- No specific context (company, role, level), so the output stays generic.
- Asking the model to “be honest” without your real track record, so it confabulates.
- Reusing one answer across companies; interviewers compare notes.
- Listing skills with no proof behind them.
- No tone anchor, so the answer lands flat.
- Skipping the fact-check; models still invent dates, titles, and figures.
How to push results further
- Paste real STAR stories so the output borrows your voice.
- Run the hostile-panelist prompt before every onsite.
- Write three drafts, ship the third; the first is generic, the second over-corrected.
- Time yourself: a 2-minute answer beats a 4-minute one.
- Read it aloud; written and spoken answers feel different.
- Keep a personal story bank and reuse your strongest stories across questions.
- Run the final answer past someone in the role; peer feedback beats AI feedback.
FAQ
- Can recruiters tell an answer was AI-written?: They rely on instinct, not detectors. The giveaways are generic phrasing and, worse, not being able to explain your own claims in the interview. Specifics fix both.
- Is it against the rules to use AI here?: Generally no. Greenhouse and others state AI assistance on applications is acceptable, and most ATS systems score role-match rather than authorship. Blandness is the real penalty.
- Which model should I use?: Claude Sonnet 4.6, GPT-5.5, or Gemini 3.1 Pro all work well for this. Pick whichever you already pay for; the task does not need a flagship.
- Should every answer follow STAR?: Behavioral answers, yes; “why this company” and philosophy questions usually do not.
- How many drafts before I’m ready?: Three for important stories, one or two for everything else.
- Should I use AI on interview day?: Only to calm nerves. Do not rewrite a prepared answer in the final hour.
- How do I keep the tone authentic?: Paste samples of your real writing into the prompt and tell the model to mirror them.