Automated Job Search Monitoring System

01What This System Does

This system automates the most time-consuming part of a professional job search: consistently monitoring job boards across dozens of target companies, deduplicating new postings, scoring them against your criteria, and logging them — without spending hours manually checking each company's careers page.

At its core, the system combines three things:

• A structured target company list — every company you care about, with direct links to their job boards
• A job log spreadsheet — a single source of truth for every role you've seen, scored, or are pursuing
• An AI sweep agent — an automated workflow that checks your Gmail alerts and each company's ATS (applicant tracking system), scores new roles, and logs everything

The result is a morning sweep that takes minutes instead of hours, surfaces only roles that match your criteria, and keeps a persistent record of your entire search. The sweep runs on demand or on a schedule, producing a structured report each time.

02Prerequisites and Tools You'll Need

Required Accounts and Access

• Gmail account — used for job alert emails from LinkedIn, Indeed, Built In, and similar job boards
• Claude Cowork (or Claude with computer use / browser access) — the AI agent that performs the sweep
• Google Chrome — the browser Claude accesses to navigate ATS job boards
• Microsoft Excel or Google Sheets — for your job log and company list

Files You'll Create

• Target_Companies.csv — your master list of companies to monitor
• job_log_MASTER.xlsx — your master job tracking spreadsheet
• A Sweep Instructions document — the prompt file Claude reads to run the sweep (described in Section 7)

Optional but Recommended

• A Gmail label or filter for job alert emails to keep them organized
• A shared cloud folder (OneDrive, Google Drive, Dropbox) so your files are accessible from anywhere

03Building Your Target Company List

Your target company list is the backbone of the sweep. The more accurate and complete it is, the better your results. Create a CSV file (Target_Companies.csv) with the following columns:

How to Find ATS URLs for Each Company

1. Go to the company's website and look for a "Careers" or "Jobs" link
2. Click through to their job listings — the URL will reveal the ATS platform
3. Use the direct API or listing URL, not just the homepage

Common ATS URL patterns:

Greenhouse:  https://boards.greenhouse.io/[token]
             or API: https://boards-api.greenhouse.io/v1/boards/[token]/jobs
Lever:       https://jobs.lever.co/[company-slug]
Ashby:       https://jobs.ashbyhq.com/[token]
Workday:     https://[company].wd[N].myworkdayjobs.com/[board-name]
iCIMS:       https://careers-[company].icims.com
Rippling:    https://ats.rippling.com/[company]/jobs
Custom:      Use the direct search results URL with a role keyword filter if possible

Tiers: How to Prioritize

• Tier 1: Companies you would proactively apply to — you're actively monitoring these and will reach out even without an inbound signal. These should be your top 50–100 companies.
• Tier 2: Companies that are acceptable if they come to you (recruiter outreach, referral, LinkedIn alert) but you won't proactively source from them. These stay in the list but get auto-skipped unless inbound.

Start with 50–75 Tier 1 companies. A list of 150+ is manageable once the sweep is automated, but a smaller, higher-quality list is better when starting out.

Whether those Tier 2 companies ever come to you depends on whether recruiters can find your profile at all. Check your profile’s findability →

How to Build Your Initial List

1. Start with companies you already know and want to work for
2. Look at LinkedIn "Companies" search filtered by your industry and size range
3. Check job boards (LinkedIn, Indeed, Built In) for which companies are actively hiring for your role type
4. Look at your network — where do people you respect work?
5. Research industry reports, "best places to work" lists, and trade publications in your field
6. Add competitors and adjacent companies to any you already have

04Building Your Job Log

Your job log (job_log_MASTER.xlsx) is a single spreadsheet that captures every role you've ever seen, scored, or pursued. It's the system of record for your entire search.

Deduplication Rule

A role is a duplicate if the Company + Role Title combinationalready exists in the log. The sweep agent checks for this before logging any new entry. Roles that are already logged get their status confirmed as "still live" but are not re-added.

Score Tier Color Coding (Optional)

Apply conditional formatting in Excel or Sheets to make the Score column visually scannable:

• GREEN (7–10): Apply — meets all primary criteria
• YELLOW (5–6): Monitor — worth a closer look, needs full JD review
• RED (1–4): Watch/Skip — logged for awareness but not worth pursuing

05Setting Up Gmail Job Alerts

Gmail job alerts are often the highest signal-to-noise source in the sweep. They surface roles from your target companies without requiring any ATS navigation.

Set Up Alerts From These Sources

• LinkedIn Job Alerts — create saved searches for your target role titles + industries + locations. LinkedIn will email you new matches daily or weekly.
• Indeed Job Alerts — same approach: saved search with email notifications.
• Career Amplifier — curated senior-level roles with strong signal-to-noise. Set up job alerts for your target function and seniority level.
• Built In — strong for tech and growth-stage companies. Sends curated alerts by city and function.
• Wellfound (formerly AngelList Talent) — best source for startup and venture-backed roles. Set a saved search with role type and stage filters.
• Glassdoor — broad coverage with salary data inline. Set job alerts on saved searches.
• The Muse — skews toward culture-forward companies and mid-market employers. Worth setting if your target companies post there.
• Ladders — focused on $100K+ roles. Useful for senior IC and director-level positions.
• Hiring Cafe — an aggregator that emails curated matches. Worth setting up if it covers your field.
• Google Alerts — set alerts for ["Your Target Role Title"] ["Your Industry"] to catch press coverage and funding announcements that mention hiring.

Gmail Search Queries for the Sweep

The sweep agent uses Gmail search to find relevant emails. The core queries:

from:jobalerts-noreply@linkedin.com newer_than:4d
from:donotreply@jobalert.indeed.com newer_than:4d
from:hello@wellfound.com newer_than:4d
from:noreply@glassdoor.com newer_than:4d
from:alerts@themuse.com newer_than:4d
from:jobalerts@ladders.com newer_than:4d
from:support@builtin.com newer_than:4d
from:elliot@bot.careeramplifier.com newer_than:4d
from:[alert-sender@hiringsite.com] newer_than:4d

Adjust the newer_than value based on your sweep frequency. For a Monday morning sweep covering the weekend, newer_than:4d catches Friday through Monday.

06The 5-Dimension Job Scoring Framework

Every role is scored on five dimensions. Dimensions 1 and 2 are primary gates— if a role fails either of them, it doesn't pass regardless of other scores. Dimensions 3–5 add nuance and drive the final score.

Scoring Guide

07Running the Morning Sweep

The sweep is a structured workflow the AI agent follows each time it runs. You give Claude a detailed instruction document (saved as a text or markdown file in your job search folder) that tells it exactly what to do.

What the Sweep Instruction Document Should Cover

1. Your identity and search context — your target role, seniority level, industries, and any absolute deal-breakers. This is how Claude knows which roles are relevant.
2. Gmail sweep instructions — which sender addresses to search, how far back to look, which inbox tabs to include.
3. ATS sweep instructions — read Target_Companies.csv, navigate to each ATS URL, search for relevant role keywords, extract new listings.
4. Deduplication rule — check job_log_MASTER.xlsx before logging anything. Skip if already logged.
5. Scoring instructions — apply the 5-dimension framework to each new role found.
6. Logging instructions — add new rows to job_log_MASTER.xlsx; update Last Checked in Target_Companies.csv.
7. Report format — how to structure the morning sweep report (see below).

Sweep Report Format

At the end of each sweep, Claude generates a structured markdown report. The report should include:

• Sweep stats: Number of companies checked, Gmail queries run, new roles found, total log rows
• New roles by score tier: GREEN (apply), YELLOW (monitor), RED (skip) — with score, verdict, and brief rationale for each
• Top picks: The 3–5 roles that need attention first and why
• Previously logged roles still live: High-value roles already in your pipeline confirmed still open
• Access failures: Any companies that couldn't be checked and why
• ATS issues to fix: Broken URLs or tokens to update before the next sweep

Typical Sweep Sequence (What Claude Does)

1. Read Target_Companies.csv to get the full company list and ATS URLs
2. Read job_log_MASTER.xlsx to load already-logged roles for deduplication
3. Search Gmail for each configured alert sender — extract role titles and companies from email content
4. For each company in Target Companies: navigate to ATS URL, search for relevant roles, extract new listings
5. For each new role: apply 5-dimension scoring, assign a verdict
6. Log all new roles to job_log_MASTER.xlsx
7. Update Last Checked date for each company in Target_Companies.csv
8. Generate and save the morning sweep report

08Automating the Sweep with Claude Cowork

Claude Cowork supports scheduled tasks — you can set the sweep to run automatically on a recurring schedule so it happens whether or not you remember to start it.

Setting Up a Scheduled Sweep

1. Open Claude Cowork and navigate to your job search folder
2. Ask Claude to create a scheduled task: "Run my job search sweep every Monday morning at [time]"
3. Point the scheduled task at your sweep instruction file
4. Verify the schedule is set correctly and confirm the first test run

The sweep will run in the background on your schedule. When it's done, the morning sweep report will appear in your job search folder, ready for review when you open your laptop.

Recommended Sweep Frequency

• Monday morning — covers all weekend postings from Friday–Monday (highest volume)
• Wednesday or Thursday — catches mid-week postings before Friday's slowdown
• On-demand — run any time you want a fresh check, especially if you're actively interviewing

Two sweeps per week is a good rhythm for an active search. Once per week is acceptable for a passive search.

09Tracking Your Pipeline

Your job log doubles as your pipeline tracker. Use the Status column to move roles through stages as you take action.

Follow-Up Cadence

Use the Next Action and Last Action Date columns to drive follow-up. A simple rule of thumb:

• After outreach: follow up in 5–7 business days if no response
• After application: follow up in 7–10 business days if no response
• After interview: follow up within 24 hours with a thank-you note
• If ghosted after two follow-ups: move to Closed, keep the company on your radar

10Continuous Improvement

The system gets better over time as you fix ATS URLs, tune your scoring criteria, and refine your target list. After each sweep, review:

• Access failures — fix broken ATS URLs before the next sweep. Each broken URL is a company you're not monitoring.
• Score calibration — if you're getting too many YELLOWs that never turn into applications, tighten your D1/D2 criteria. If you're getting too few results, check whether your keyword search is too narrow.
• Company list health — add companies you discover during the sweep. Remove companies that have been dormant for 3+ months or that have clearly stopped hiring in your function.
• Gmail alert coverage — if a role from a target company showed up somewhere unexpected, add that source to your alert setup.

This guide covers a generic implementation of the automated job search monitoring system. Adapt the scoring framework, company list, and sweep schedule to your specific search context.