Here's the part nobody's loud enough about: humans don't read résumés first anymore — AI does. Applicant tracking systems screen them, recruiter copilots summarize them, and most hiring managers don't see your résumé until an AI has already decided whether to surface it. So if AI is the first reader, the smart move is to refine your résumé using AI. WaxFrame runs a hive of them — ChatGPT, Claude, Gemini, and more — on your résumé at once, catching the lazy bullets, weak verbs, and missing metrics before the bots do.
Free 3-round trial — no signup, no credit card. Unlock unlimited rounds with a $19 lifetime license. Open WaxFrame ↗ · Résumé Template ↗
True story: WaxFrame's creator landed his current job by doing exactly this process by hand. He took a 20-year-old résumé, opened up ChatGPT, Claude, and Gemini in separate tabs, fed the same draft into each, collected their notes, reconciled the suggestions himself, then ran it through them again. Four or five rounds in, the résumé that came out the other side was the one that got him hired.
That manual back-and-forth was the prototype for WaxFrame. The app exists because the result was that much better than any single AI on its own — but the manual version was tedious enough that nobody would do it twice. WaxFrame is that workflow with the tedium removed: paste the résumé once, the hive reviews in parallel, a Builder synthesizes the consensus, you decide what to keep.
You are not the first person to use a hive of AIs to refine a résumé. You're just the first person to do it without 47 browser tabs.
Modern résumé screening is layered. First the ATS keyword-matches against the job description. Then a recruiter copilot summarizes — bullet by bullet — what you've done and how well it maps to the role. Only then does a human spend 7-10 seconds scanning the result. Every layer has different failure modes: ATS misses you for missing the right phrase, the copilot flattens your bullets if they're not specific, the human bounces if the summary doesn't land.
A single AI catches the obvious problems — weak verbs, passive voice, missing metrics. A hive catches all of them plus the subtle ones: bullets that an ATS will miss because the keyword is buried, claims a recruiter copilot will downgrade as inflation, accomplishments a human will skim past because the metric isn't in the first half of the line, chronology gaps the reader will assume the worst about.
WaxFrame runs ChatGPT, Claude, Gemini, Grok, and DeepSeek on your résumé at once. Each returns numbered, specific suggestions — "bullet 3 under [Company] is a duty not an accomplishment," "the metric in bullet 1 needs a baseline," "the skills section duplicates content already in the bullets," "the summary reads as job-seeker-speak," "the job-description keyword 'cross-functional' isn't anywhere in your draft." A Builder AI synthesizes the strongest into a refined version. You review every change.
Will: turn duties into accomplishments (added "$2M pipeline / 40% conversion lift / 8-person team" where you wrote "managed sales pipeline"), strengthen weak verbs ("Led" instead of "Was responsible for"), surface missing metrics on real accomplishments, flag bullets that are too long for scan-reading, calibrate the summary to read as a positioning statement not a wishlist, kill duplicated content between bullets and skills, kill jargon that doesn't earn its keep, flag chronology gaps that need explanation.
Won't: invent jobs, manufacture employers, fabricate metrics, lie about your skills, or claim degrees you don't have. The Builder is explicitly instructed never to add facts that aren't in your draft. If a bullet has no metric and you don't supply one in the Notes drawer, the reviewer will flag it but won't make one up.
Open WaxFrame, pick the Résumé template, paste your current résumé into the Starting Document screen. If you're targeting a specific role, paste the job description into Reference Material — the hive will check your bullets against the listed requirements every round. Pick a Builder AI (Claude for tone, ChatGPT for bullet rewrites). Run 3-6 rounds. Export when satisfied.
Same template, but click Start from Scratch on the Starting Document screen. In the Notes drawer before Round 1, paste your career history: company, title, dates, three or four things you actually did and the impact. The hive will turn each item into accomplishment-format bullets, calibrate the summary, and build out the skills section. Don't worry about phrasing — bullet-writing is exactly what the hive is for.
If you paste the job description into Reference Material, every reviewer will check your bullets against the requirements. They'll flag where your résumé matches strongly, where it matches weakly, and where you have a relevant accomplishment that's currently buried. That's the difference between "a polished résumé" and "a polished résumé tuned to this role."
WaxFrame handles 10,000+ characters of reference material — paste the full posting, not just the bullet points.
Round 1. Six reviewers flag: summary is generic, three bullets are duties not accomplishments, two bullets are missing metrics, the skills section duplicates content, a 2022 gap needs framing. Builder rewrites with all fixes. You accept five of six. You add the missing metrics from memory in the Notes drawer.
Round 2. Reviewers flag: bullets are sharper, but the summary still reads like a wishlist, two verbs are weak, the chronology framing for 2022 is clear but a touch defensive. Builder rewrites. You accept all.
Round 3. Reviewers flag: summary lands, verbs are strong, but two bullets are over a line and a half — won't scan. Builder tightens. You accept.
Round 4. Four reviewers return NO CHANGES; two flag final polish (parallel verb tense in one job, one stray Oxford comma inconsistency). Builder applies. You export to .docx.
Total time: ~20-30 minutes. Total API cost: usually well under $1 on a paid Builder.
Document type set to "Résumé." Target audience pre-scripted ("Recruiter or hiring manager doing a 7-10 second scan first, then a deeper read if the scan lands"). Desired outcome pre-scripted ("Reader wants to interview me. Bullets are accomplishments with metrics, not duties. Summary positions, not wishes. Skills back up the bullets, don't duplicate them"). Scope & constraints already populated ("No 'responsible for'. No 'wears many hats'. No 'team player'. Every bullet starts with a strong verb. Metrics on every accomplishment that has one"). Reference Material field labeled for the job description when targeting a specific role. Best AIs For: Claude for tone and authenticity, ChatGPT for bullet rewriting, Grok for verb sharpening.
Every field is editable once the template loads.
1. Open WaxFrame. waxframe.com ↗ — runs in your browser, no install, no signup. Works on desktop and laptop (Chrome, Firefox, Edge, Safari at 1366×768 or wider).
2. Apply the Résumé template from the Template Catalog ↗ — auto-populates the Goal fields.
3. Want the deep version of this workflow? See the Résumé playbook ↗ — every field, every option, with reasoning.
4. Cost question? See AI API Pricing ↗ — live per-token rates for every supported provider.
WaxFrame is fully open source under the AGPL-3.0 license. Every line of code is public and auditable.
💡 Your API keys go directly from your browser to each AI provider. WaxFrame never sees them. Read the source on GitHub →
About
Built with ❤️ by WeirDave and Claude.
Your WaxFrame Pro license is active.