Back/Personal/Claude
AdvancedPersonal

Create a Personalized AI-Powered Job Board for a Smarter Job Hunt

Build an automated system that scours the web for job openings, uses AI to score them for relevance against a personal profile, and delivers a curated list of the best opportunities to you daily.

Create a Personalized AI-Powered Job Board for a Smarter Job Hunt

36:45 to 42:59: Alex Lieberman describes a personal job-search system that collects openings, scores them against his profile, and delivers the best matches each day.

Before you start

What you need

  • A candidate profile with must-haves, preferences, and deal breakers
  • Trusted job sources and search queries
  • A scoring rubric plus a destination for the daily digest

What you’ll make

A daily shortlist of current openings ranked against explicit role, company, location, and experience preferences.

Tools used

Step by step

The workflow

Follow the sequence once, then adapt the prompts, checks, and handoffs to your own setup.

5 steps

Step01

Define Your Ideal Job Criteria

Write a detailed profile of your ideal job, including key skills, desired company stage, and experience level. This profile will serve as the rubric for the AI to score job descriptions.

Example prompt
Write a detailed profile of your ideal job, including key skills, desired company stage, and experience level. This profile will serve as the rubric for the AI to score job descriptions.

My actual values:
[insert the files, settings, accounts, or constraints for this step]

Give me the exact commands, settings, or output to use. Finish with a pass or fail check for define your ideal job criteria.
Step02

Set Up Automated Web Scraping

Use a tool like Firecrawl to set up a daily scraper for your target job boards. The script should extract the raw text from new job postings for AI analysis.

Example prompt
Use a tool like Firecrawl to set up a daily scraper for your target job boards. The script should extract the raw text from new job postings for AI analysis.

My actual values:
[insert the files, settings, accounts, or constraints for this step]

Give me the exact commands, settings, or output to use. Finish with a pass or fail check for set up automated web scraping.
Step03

Feed Job Descriptions to AI for Scoring

Feed the raw text from each scraped job description into an AI model like Claude. Prompt it to score the job's relevance against your personal profile.

Example prompt
Sample prompt concept: 'Given the following job description and my personal profile [insert profile/criteria], score this job's relevance for me from 1-10. Explain your reasoning briefly.'
Step04

Curate and Summarize the Top Results

Instruct the AI to filter the scored results, selecting only jobs above a certain threshold, for example, 8 out of 10. For these top jobs, ask for a brief summary.

Example prompt
Here is a list of jobs I have scored for relevance against my personal profile. [paste list of jobs with their scores] Your task is to:
1. Select only the jobs with a score of 8 or higher.
2. For each selected job, write a 2-3 sentence summary covering the role's core responsibilities and why it might be a good fit based on the original job description.
3. Present the results as a clean, numbered list with the job title, company, and your summary.
Step05

Automate Daily Delivery

Set up an automated job to email the curated and summarized list of the top 10 job openings to you every morning.

Example prompt
Set up an automated job to email the curated and summarized list of the top 10 job openings to you every morning.

My actual values:
[insert the files, settings, accounts, or constraints for this step]

Give me the exact commands, settings, or output to use. Finish with a pass or fail check for automate daily delivery.

What good looks like

  • Every recommended role is still open and links to the original posting
  • The score explains the match and any missing requirement
  • Duplicate and previously rejected jobs do not return in later digests

Build your next product with ChatPRD

Turn an idea into a PRD, user stories, and a plan.

Try ChatPRD free

After the steps

Runbook notes

How to recover when the loop fails and where human judgment helps.

Recover

If it goes sideways

The system recommends impressive jobs that violate a must-have
Separate hard filters from scoring preferences and discard failures before ranking.
The digest fills with duplicate or expired listings
Store canonical job URLs and first-seen dates, then recheck availability before delivery.

Start shipping
better products.

Join 100,000+ product managers who use ChatPRD to write better docs, align teams faster, and build products users love.

Free to start
No credit card
SOC 2 certified
Enterprise ready