AI Automated Job Application System — Research Every Role, Tailor Every Application and Track Every Submission So You Can Apply to More Jobs
Built by FiberStream ·
About this build
A Claude and n8n powered workflow that takes a job posting URL, researches the company, rewrites your CV and cover letter specifically for that role, scores your application fit before you submit and logs everything to a tracking dashboard — turning a 3 hour manual process into under 8 minutes per application.
What was built
Built this during an active job search in Australia when the manual process was taking more time than the actual job applications deserved. The research phase alone was 45 to 60 minutes per role on SEEK and LinkedIn. CV tailoring another 45 minutes. Cover letter another hour. By the time one strong application was ready the morning was gone. The workflow runs from two inputs — paste a job posting URL and your base CV and everything else happens automatically. Step 1 — Job posting extraction n8n fetches the job posting and Claude parses it into a structured format — role title, company, key responsibilities, required skills and language signals in the posting that reveal what this company actually values beyond the listed requirements. Mirroring that language significantly increases match rate with Australian Applicant Tracking Systems used by most medium to large employers. Step 2 — Company research via Perplexity Four targeted searches run automatically. Recent news and announcements. Current product or service offering. Their culture and values from their website and Glassdoor Australia. Any funding, growth or strategic developments suggesting why they are hiring right now. Understanding why a company is hiring right now is the single most valuable output. A Melbourne startup that just raised Series A hiring a Head of Marketing is a completely different application to a Sydney enterprise replacing a departing employee. Step 3 — CV tailoring via Claude Claude scores each experience on the CV for relevance to this specific role, rewrites the professional summary to reference the company’s current situation and reorders achievements within each role to lead with the most relevant items for this hiring manager rather than the most impressive items in absolute terms. Step 4 — Cover letter generation via Claude Written in a strict 4 paragraph structure that consistently outperforms generic cover letters. Paragraph 1 — opens with something specific about the company from the research that signals genuine interest. Not I have long admired your company — a specific recent development that connects to why this role is interesting right now. Paragraph 2 — the most relevant single achievement from the CV told as a brief story with a specific measurable result. Paragraph 3 — how the applicant’s specific background addresses the primary challenge implied by the job posting using the company’s own language from Step 1. Paragraph 4 — brief close with a specific next step. Total length under 300 words. Australian hiring managers consistently read shorter cover letters more often than longer ones. Step 5 — Application fit score Claude generates a fit score out of 100 across 5 dimensions — skills match, experience level match, industry match, culture signal match and application strength. Any dimension scoring below 6 gets flagged with a specific explanation and a recommendation — apply anyway, address the gap directly in the cover letter or skip this role. This prevented several applications to roles that looked right on the surface but had a fundamental mismatch that would have been obvious to the hiring manager. Step 6 — Airtable tracking Every application gets logged automatically with the company, role, date, fit score, CV version used and current status. Follow-up reminders fire 7 days after submission if no response received — a single Slack prompt to send a brief polite follow-up. Results after 8 weeks of active job searching: 47 applications submitted. Average time per application — 7 minutes 43 seconds versus previous 2 hours 51 minutes. Interview rate — 34 percent compared to the 8 to 12 percent typically reported for Australian job markets. Two hiring managers specifically mentioned the cover letter standing out during the interview itself. The fit score proved most valuable when it flagged a role I was genuinely excited about as 4 out of 10 on experience level match. Applied anyway. Did not progress. The data was there to make the decision consciously rather than hopefully. Will share the full n8n workflow JSON, Perplexity research prompts and Claude generation prompts in comments for anyone building their own.