You can spot an AI-written resume in about four words — usually “results-driven professional.” Same buzzwords every time, same faint smell of a chatbot that never met you. Tailor is the antidote. You paste in a job description, and it hands back a resume and cover letter tuned to that job — grounded in your actual experience, and written in your voice, not a model’s default one.
Here’s the trick that makes it different: grounding is non-negotiable. Tailor works from a “master resume” — your real career history, every role and bullet with a stable id. When it tailors a resume to a posting, every line it writes has to trace back to something you actually did. Anything ungrounded gets rejected before it ever hits the page. So it reorders, reframes, and emphasizes to fit the job… but it never invents a skill you don’t have or a job you never worked. No hallucinated accomplishments, ever.
The voice half is the other piece. Instead of one flat “professional” tone, Tailor learns yours — from a short guided interview, from writing samples you paste in, and over time from the edits you make before you export. It distills all that into a voice profile that shapes the wording (never the facts). Cover letters lean on it hardest, which is exactly where the generic-chatbot smell is worst.
It started life as a single-user tool I ran on my own laptop to stop rewriting
my resume by hand for every application. Over the last stretch it grew up into a
real multi-user web app — a Flask backend with Postgres, Clerk for sign-in,
Stripe for a fair trial-then-pay model, Claude doing the tailoring under prompt
caching to keep per-run cost sane, python-docx exporting a clean .docx, all of
it running on AWS behind Terraform. It’s live.
Who’s it for? Anyone tired of the resume treadmill — job switchers, career-changers, anyone applying to more than one place and unwilling to send the same generic PDF to all of them. You get a document that’s honest to your history and sounds like you wrote it, in the time it takes to read the posting.
The code is public: github.com/eventually-consistent-code/tailor.