AI Automated Job Application System — Research Every Role, Tailor Every Application and Track Every Submission Without Spending 3 Hours Per
Built by RadianHelix ·
About this build
A Claude and n8n powered workflow that takes a job posting URL, researches the company in depth, rewrites your CV and cover letter specifically for that role, scores your application fit before you submit and logs everything to a tracking dashboard — collapsing a 3 hour manual process into under 8 minutes per applicati
What was built
Built this during an active job search when I realised I was spending more time preparing applications than actually applying. The research phase alone was taking 45 to 60 minutes per role. CV tailoring another 45 minutes. Cover letter another hour if done properly. By the time one strong application was ready the day was gone. The workflow runs from two inputs — paste a job posting URL and your base CV into a form and everything else happens automatically. Step 1 — Job posting extraction n8n fetches the job posting URL and extracts the full text. Claude parses it into a structured format — role title, company, key responsibilities, required skills, preferred skills, seniority level and language signals in the posting that reveal what the company actually cares about beyond the listed requirements. The language signal analysis is what most applicants skip — companies consistently use specific words in job postings that reveal culture and priorities and mirroring that language significantly increases match rate with applicant tracking systems. Step 2 — Company research via Perplexity Four targeted searches run simultaneously. Recent news and announcements from the last 90 days. Current product or service offering. Stated values and culture from their website and Glassdoor. Any funding, growth or strategic developments that suggest why they are hiring for this role right now. The why they are hiring now question is the most valuable output. A company that just raised a Series B hiring a Head of Marketing is a completely different situation to a company replacing a departing employee. The application should reflect which situation applies. Step 3 — CV tailoring via Claude The base CV and structured job posting analysis get passed to Claude which scores each experience for relevance to this specific role, rewrites the professional summary to reference the company’s current situation and reorders skills and achievements within each role to lead with the most relevant items rather than the most impressive ones in absolute terms. Step 4 — Cover letter generation via Claude Written using a strict 4 paragraph structure. Paragraph 1 — opens with something specific about the company from the research that signals genuine interest. Not I have always admired your company — a specific recent development connecting to why this role is interesting right now. Paragraph 2 — the most relevant single achievement 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 call to action. Total length — under 300 words. Hiring managers consistently read shorter cover letters more often than longer ones. Step 5 — Fit score before submitting 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 suggestion for whether to apply anyway, address the gap directly in the cover letter or skip this role entirely. The fit score 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 — saving the time of preparing and submitting something unlikely to progress. Step 6 — Airtable tracking Every application gets logged automatically with the company name, role, date, fit score, CV version used, whether a cover letter was submitted and current status. Follow-up reminders fire automatically 7 days after submission if no response has been received. What broke during development: The CV reordering was too aggressive early on — Claude was removing experience it deemed irrelevant rather than reordering. Fixed by changing the instruction from optimise to reorder and expand or contract — the base experiences must stay, only their prominence changes. The cover letter first paragraph kept defaulting to generic admiration despite specific instructions. Fixed by providing 3 examples of bad first paragraphs and 3 examples of good ones directly in the prompt — showing the contrast was more effective than describing it. Results after 8 weeks: 47 applications submitted. Average time per application — 7 minutes 43 seconds versus previous 2 hours 51 minutes. Interview rate — 34 percent compared to 8 to 12 percent industry average for similar roles. Two hiring managers specifically mentioned the cover letter standing out during the interview itself. Will share the full n8n workflow JSON and Claude prompt structure in comments for anyone who wants to deploy this.