By Jeff Altman, The Big Game Hunter

Manual data entry and repetitive workday forms turn job hunting into an exhausting second shift. This framework integrates Claude, Playwright MCP, and Google Sheets to extract listings, match targeted resumes, and auto-submit applications without hallucinations. We’ll explain how to compress 20 weekly hours of manual submissions into a 20-minute daily review routine while tripling recruiter response rates.

Finding open roles, tailoring resumes, and filling out the exact same Workday forms 30 times a week takes an enormous amount of energy. The cognitive overhead turns the search itself into a grueling full-time job. By stacking a few specific tools—Claude, Claude Cowork, Google Sheets, and a browser agent—you can construct an engine that handles that repetitive work for you. Instead of spending 20 hours a week manually entering data, you can compress the entire process down to a 20-minute daily routine of reviewing and approving applications. We are going to build a personalized, autonomous career assistant that runs your application pipeline from discovery to submission.

First, we have to give the AI a way to interact with the internet. On its own, a text-based model cannot open a webpage, read a dynamic form, or click a submit button. To solve this, we use Playwright MCP. This is a Model Context Protocol—a bridge that connects Claude to a functional, automated web browser. To set it up, you run a single installation command in your terminal and then auto-allow the permissions in Claude’s configuration file. This prevents the system from pausing to ask you for approval on every single action. With that protocol running, Claude gains the ability to open new tabs, type text into fields, and upload PDFs exactly the way a human applicant would.

Next, you need a central hub to manage your leads. A simple Google Sheet works perfectly. You set up dedicated columns with headers for the company, the role, the application link, and the status. Let’s look at this diagram mapping how we pull the job data into that sheet. You might be tempted to ask Claude to scrape company websites directly, but doing that burns through your usage rate limits quickly. It often results in silent failures where jobs simply stop appearing on your list without any error warning. Instead, you run your search through dedicated scraping APIs, like Apify or Jobright. These tools are built specifically to extract leads, bypassing the blocks that normally stop AI agents. Decoupling the discovery phase from Claude ensures you get a continuous, reliable feed of curated job listings deposited directly into your spreadsheet every morning.

Before the agent starts applying to those leads, you need to prepare your materials. Having one generic resume creates a broad, uncompetitive profile. Write two or three highly tailored PDF resumes, each optimized for a specific job family you want to target. You then instruct Claude to navigate to a job URL from your spreadsheet, scan the requirements, and score the job description against your available resumes to select the strongest match.

This is where you must set a strict boundary in your prompt. You have to explicitly forbid the AI from inventing facts or exaggerating metrics to fit the job requirements. If your document says you managed 20 people, the AI cannot round that up to 50. Once the right document is chosen, the browser agent maps that specific resume’s data directly into the blank fields of the employer’s application form. By defining those strict mapping rules upfront and using highly targeted documents, the engine scales your application volume without sacrificing the precision and accuracy of a human-tailored approach.

Even with targeted applications, standard pipelines yield a response rate of roughly 5%. To push that number higher, we automate the post-application networking: the recruiter follow-up email. We set up a trigger sequence using Claude Cowork. The moment a job status updates to “applied” in your Google Sheet, the sequence activates. Cowork acts as the connective tissue for this task. It pulls in the job description you applied for and cross-references it with the exact resume the agent submitted. Using that context, it drafts a concise, three-sentence message referencing a specific requirement from the posting. It drops this draft into a 48-hour delay queue for you to review and send.

Consistently writing and sending these messages manually leads to rapid burnout. By automating this connective tissue, you ensure every single application gets a targeted follow-up with zero added cognitive overhead—a consistency that has been shown to push response rates from a baseline of 5% to 15%. You now have an architecture that independently pulls fresh leads, applies to them using the optimal resume, and queues up highly personalized recruiter follow-ups. The search process is no longer a second job. Your responsibility shifts from endless manual data entry to a simple 20-minute routine where you check the sheet and approve the AI’s outbound messages.

There’s a lot more to help you at JobSearch.Community. Become an insider and get coaching from Jeff Altman, as well as video courses, books, and guides to help you. Or you can purchase individual products and services à la carte. Jeff has helped tens of thousands of people land new jobs using techniques he learned while working in search. It’s just the way it is. If you like the video, share it, leave a comment, click the like button, and follow the channel. It will help other people if you do. If you want to thank me for the advice, buy me a coffee. The link is in the show notes.

Overcoming Ageism in Your Job Search as an Experienced Professional

ABOUT JEFF ALTMAN, THE BIG GAME HUNTER

People hire Jeff Altman, The Big Game Hunter to provide No BS job search coaching and career advice globally because he makes job search and succeeding in your career easier. 

38 Deadly Interview Mistakes to Avoid

You will find great info and job search coaching to help with your job search at ⁠⁠JobSearch.Community⁠⁠ 

Connect on LinkedIn: ⁠https://www.linkedin.com/in/T⁠⁠heBigGameHunter⁠