The Cover Letter That Is Not Generic
Write a cover letter that could only have been written by you, for this job. Tests whether you can force specificity out of a model that defaults hard to platitudes.
Why this one
The test for a cover letter is simple: swap the company name for another and see if it still works. If it does, it says nothing. Almost every AI-generated cover letter fails this test on the first attempt.
Steps
Find three specifics about the company
A recent product decision, something in their engineering blog, a stated value visible in how they actually operate. Do this research yourself — a model asked to research a company will produce plausible generalities.
Find three specifics about yourself that connect
Not "I am a hard worker" but "I spent two months on the same class of problem you described in that post". The connection between the two lists is the entire letter.
Write with the substitution test built in
Give the model both lists and the test itself as a constraint.
PromptWrite a cover letter for [role] at [company]. WHAT I KNOW ABOUT THEM: [your three specifics] WHAT I HAVE DONE THAT CONNECTS: [your three specifics] Hard rules: - Every paragraph must reference something from one of the two lists - If I swapped the company name for a competitor, the letter must stop making sense - No sentence may work equally well for any other applicant - 250 words maximum - Do not open with "I am writing to apply"
Run the substitution test
Replace the company name with a competitor and read it again. Every sentence that still works is a sentence to cut or rewrite. Usually that is more of the letter than you would like.
You should end up with
A cover letter that fails the substitution test — in the good way.
Done when
- Swapping the company name makes the letter nonsensical
- Every paragraph contains a verifiable specific
- It is under 250 words
If you want to go further
- Write a second version for a company you would not want to work for and notice how much harder it is
Try next
Topics
Related across the site
AI agent
An AI agent is a system where a model plans and takes actions through tools in a loop, rather than producing a single response. It decides what to do next, does it, observes the result, and continues until the goal is met.
AI Marketing
Use AI for market research, copywriting frameworks, and audience segmentation — with prompts that produce genuinely usable marketing assets, not generic filler.
AI SEO & Search Visibility
Use AI to do keyword research, optimize content for search, and get your brand cited by AI answer engines like ChatGPT, Perplexity, and Google AI Overviews.
Build a Personal Study Assistant
Turn a stack of lecture notes into a study partner that quizzes you, explains what you got wrong, and tracks which topics you keep failing. You will finish with a reusable system prompt you can point at any subject.
Build a Research Brief Generator
Create a repeatable workflow that turns a vague question into a structured research brief with sources, open questions and a confidence rating. The output is something you can hand to a colleague, not a wall of text.
Competitor Content Gap Analysis
Paste a competitor's page structure (headings, topics covered) alongside yours and ask AI to find gaps — subtopics they cover that you don't, questions they answer, and angles they missed that you can own..