Agentic Classroom

How to Make AI Track Your Job Applications

Applied to dozens of jobs. Forgot who to follow up with.

How to Make AI Track Your Job Applications

Applied to dozens of jobs. Forgot who to follow up with. Ten minutes now means you never lose a lead to a messy memory or a scattered WhatsApp note again.

Setup time About 10 minutes
Tracker columns Company, Role, Date Applied, Status, Follow-up Date
Connection method MCP (Model Context Protocol)
Typical follow-up window 7 to 14 days after applying

1. Make one simple tracker

Open a Google Sheet or Notion page with five columns: Company, Role, Date Applied, Status, Follow-up Date. One row per application, nothing fancy. This becomes the single place your AI checks and updates.

2. Connect your AI to it

Many AI assistants can now connect to Google Sheets or Notion through a feature called MCP, which simply means your AI can open and edit real apps, not just chat about them. Turn it on once in your assistant’s settings and point it at your tracker. No such option yet? Paste the sheet’s rows into the chat whenever you need it, it still works.

3. Log every application in one line

Right after you apply, tell your AI: ‘Add this to my tracker: Infosys, Business Analyst, applied today, follow up in 7 days.’ It fills the row and works out the follow-up date. Ten seconds, and you never open the sheet by hand.

4. Ask it who needs a nudge

Once a week, ask: ‘Which applications are due for a follow-up?’ Your AI scans the sheet and names exactly who to email, based on the dates you already gave it. No more scrolling your memory trying to recall who you applied to in June.

5. Let it draft the nudge

Ask it to write the follow-up too: ‘Draft a short, polite follow-up for the Business Analyst role at Infosys, applied 7 days ago.’ You just check it and hit send. Tracking and writing both come out of the same ten-minute setup.

A worked example

A reader applying to fifteen roles over a month while still working full time.

Before

A messy phone note: ‘Infosys – applied?, TCS 2nd week, Wipro follow up??’

After

A clean sheet the AI keeps updated, and a weekly message from it: ‘Follow up due: TCS (Data Analyst, applied 9 days ago), Wipro (applied 8 days ago). Want me to draft both?’

Three ways to bend it

For salespeople

Use the same tracker for leads instead of jobs: Company, Contact, Last Call Date, Next Step. Ask your AI weekly which leads have gone quiet and need a nudge.

For freelancers

Track invoices: Client, Amount, Date Sent, Paid Yes or No. Ask AI which invoices are more than fifteen days overdue and let it draft the payment reminder.

For recruiters

Track candidates instead of jobs: Name, Role, Stage, Last Contact. Ask AI who has been sitting in the same stage for over a week.

When it goes wrong

My AI doesn’t have an option to connect to Sheets.

Skip the connection step. Paste the current rows into the chat each time you ask a question. It’s one extra copy-paste but the tracking logic still works fine.

It keeps getting the follow-up date wrong.

Give it the exact date you applied instead of words like ‘today’. AI is far more reliable with a specific date than with relative time.

I forget to log the application in the first place.

Attach it to something you already do. Log it the moment you close the application tab, not later at the end of the day when you’ve forgotten.

When not to use this

If you’re only applying to two or three roles a month, keep it simple, a spreadsheet in your head works fine and this setup is overkill. This is for the stretch of a serious job hunt where you’re applying daily and start losing track of who you already followed up with. One more thing, always review the follow-up message before it goes out. Never let AI send it untouched. A wrong company name in an automated message looks worse than sending no follow-up at all.

What you can now do

You stop losing job applications to memory, and start following up on every single one without carrying the list in your head.

Part of Making Life Easier With AI, a weekly walk-through of one small thing AI can take off your plate.

Take this further

Full resume rewrite, section by sectionBest on Claude
Act as a blunt hiring manager who has read ten thousand resumes, not a career coach. I will paste my full resume and the job description I want. Rewrite the whole resume for that role, section by section, in this order: summary, experience, skills, education. Rules: every experience line leads with impact, not duty. Use bracketed placeholders like [8 percent] for any number I did not give you, and list at the end every placeholder I need to replace with a real figure. Keep it to one page of text. Plain formatting only, no tables or columns, so screening software can parse it. After the rewrite, tell me the three weakest claims that need evidence before I send this anywhere. My resume: [paste resume]. The role: [paste job description].

Takeaways

  • Create a five-column tracker in Google Sheets or Notion before your next application, not after.
  • Give your AI the exact date you applied rather than words like today so follow-up dates stay accurate.
  • Ask your AI weekly which applications are due for a follow-up instead of scrolling back through memory.
  • Always review any AI-drafted follow-up message for correct company and role names before sending it.
  • If your AI cannot connect via MCP, paste your tracker rows into the chat each time as a workaround.

Questions people actually ask

How do I get AI to track my job applications automatically?

Set up a simple tracker in Google Sheets or Notion with columns for Company, Role, Date Applied, Status, and Follow-up Date. Connect your AI assistant to it using MCP (Model Context Protocol), a standard that lets AI open and edit real apps instead of just chatting. If your assistant lacks that option, paste the sheet’s rows into the chat each time.

What is MCP and why does it matter for job tracking?

MCP, short for Model Context Protocol, is an open standard from Anthropic that lets AI assistants connect directly to apps like Sheets or Notion and read or write real data, not just discuss it. For job tracking, it means you can tell your AI to log an application or check follow-ups without manually opening the sheet yourself.

How many days after applying should I follow up on a job?

Most career advice suggests waiting about 7 to 14 days after applying before sending a follow-up, unless the posting lists a closing date, in which case wait a day or two after that passes. Giving your AI tracker an exact follow-up date rather than a vague timeframe keeps the reminders accurate.

What if my AI assistant can’t connect to Google Sheets or Notion?

Skip the MCP connection step entirely. Copy and paste the current rows from your tracker into the chat whenever you want your AI to check follow-ups or log a new application. It is one extra step each time, but the tracking and reminder logic works exactly the same way.

Is it worth setting up an AI tracker if I only apply to a few jobs a month?

Probably not. This kind of setup pays off when you are applying daily during an intense job search and start losing track of who you already contacted. For two or three applications a month, a simple mental note or basic spreadsheet is usually enough without the extra setup.

Sources

  1. Introducing the Model Context ProtocolAnthropic
  2. Connect AI tools with Notion MCPNotion
  3. Configure the Sheets MCP serverGoogle for Developers

What happens next

Expect more AI assistants to ship native MCP connectors for Sheets and Notion over the next year, which should shrink the paste-your-rows workaround described here. Watch whether job boards or ATS platforms start exposing their own MCP-style hooks, since that would let a tracker pull applied and viewed statuses automatically instead of relying on manual logging.

Share this
About the author
Vinayak Kapoor
Vinayak Kapoor

Vinayak started at seventeen on a call centre floor and climbed every rung himself over fifteen years: millions of customer conversations for some of the world's largest brands, self-taught design, video and web work, a profitable e-commerce brand of his own, and now human cyber risk, where he has built customer success journeys for national critical infrastructure and leads business growth at HumanFirewall. Nobody groomed him. He learned every skill alone, including the AI he now builds with daily as founder of Quarry, MaaSify and HuMatrix. He writes here so your career gets the guide his never had.

Read next
Come find me

The daily thinking
lives on the feeds.

Long form here. The working notes, the arguments and the things that did not fit go out most days.

← All writing