Build a Crew to Tailor your Resume to Job Descriptions¶

import os
os.environ["OPENAI_API_KEY"] = 'sk-proj-....'
os.environ["OPENAI_MODEL_NAME"] = 'gpt-3.5-turbo'
os.environ["SERPER_API_KEY"] = '..' # get here https://serper.dev/api-keys

from crewai import Agent, Task, Crew

# Importing built in tools
from crewai_tools import (
  FileReadTool,
  ScrapeWebsiteTool,
  MDXSearchTool,
  SerperDevTool
)
scrape_tool = ScrapeWebsiteTool()
search_tool = SerperDevTool()
read_resume = FileReadTool(file_path='harsharesume.md')
semantic_search_resume = MDXSearchTool(mdx='harsharesume.md')

from crewai.tools import BaseTool
from pydantic import BaseModel, Field
from datetime import datetime

# Define the input schema for the tool
class ExperienceInput(BaseModel):
    start_date: str = Field(description="Start date of the job in YYYY-MM-DD format")
    end_date: str = Field(description="End date of the job in YYYY-MM-DD format. Use 'Present' if currently employed.")

# Define the custom tool class
class ExperienceCalculatorTool(BaseTool):
    name: str = "Experience Calculator"
    description: str = "Calculates the total years of experience given a start and end date."
    args_schema: type[BaseModel] = ExperienceInput

    def _run(self, start_date: str, end_date: str) -> str:
        try:
            start = datetime.strptime(start_date, "%Y-%m-%d")
            if end_date.lower() == 'present':
                end = datetime.now()
            else:
                end = datetime.strptime(end_date, "%Y-%m-%d")

            years = (end - start).days / 365.25
            return f"{years:.1f} years"
        except ValueError:
            return "Error: Invalid date format. Please use YYYY-MM-DD."

# Initialize the custom tool
calc_experience = ExperienceCalculatorTool()

# Agent 1: Researcher
researcher = Agent(
    role="Tech Job Researcher",
    goal="Make sure to do amazing analysis on job posting to help job applicants",
    tools = [scrape_tool, search_tool],
    verbose=True,
    backstory=(
        "As a Job Researcher, your prowess in navigating and extracting critical information from job postings is unmatched."
        "Your skills help pinpoint the necessary qualifications and skills sought by employers, forming the foundation for effective application tailoring."
    )
)

# Agent 2: Profiler
profiler = Agent(
    role="Personal Profiler for Engineers",
    goal="Do incredible research on job applicants to help them stand out in the job market",
    tools = [scrape_tool, search_tool, read_resume, semantic_search_resume, calc_experience],
    verbose=True,
    backstory=(
        "Equipped with analytical prowess, you dissect and synthesise information from diverse sources to craft comprehensive personal and professional profiles, laying the groundwork for personalized resume enhancements."
    )
)

# Agent 3: Resume Strategist
resume_strategist = Agent(
    role="Resume Strategist for Engineers",
    goal="Find all the best ways to make a resume stand out in the job market.",
    tools = [scrape_tool, search_tool, read_resume, semantic_search_resume],
    verbose=True,
    backstory=(
        "With a strategic mind and an eye for detail, you excel at refining resumes to highlight the most relevant skills and experiences, ensuring they resonate perfectly with the job's requirements."
    ),
    allow_delegation=True # Enables the agent to talk to others
)

# Agent 4: Interview Preparer
interview_preparer = Agent(
    role="Engineering Interview Preparer",
    goal="Create interview questions and talking points based on the resume and job requirements",
    tools = [scrape_tool, search_tool,
             read_resume, semantic_search_resume],
    verbose=True,
    backstory=(
        "Your role is crucial in anticipating the dynamics of interviews."
        "With your ability to formulate key questions and talking points, you prepare candidates for success, ensuring they can confidently address all aspects of the job they are applying for."
    )
)

# Task for Researcher Agent: Extract Job Requirements
research_task = Task(
    description=(
        "Analyse the job posting URL provided ({job_posting_url}) to extract key skills, experiences, and qualifications required."
        "Use the tools to gather content and identify and categorise the requirements."
    ),
    expected_output=(
        "A structured list of job requirements, including necessary "
        "skills, qualifications, and experiences."
    ),
    agent=researcher,
    async_execution=True
)

# Task for Profiler Agent: Compile Comprehensive Profile
profile_task = Task(
    description=(
        "Compile a detailed personal and professional profile using the GitHub ({github_url}) URLs, and personal write-up ({personal_writeup})."
        "Utilise tools to extract and synthesise information from these sources."
    ),
    expected_output=(
        "A comprehensive profile document that includes skills, project experiences, contributions, interests, and communication style."
    ),
    agent=profiler,
    async_execution=True
)

# Task for Resume Strategist Agent: Align Resume with Job Requirements
resume_strategy_task = Task(
    description=(
        "Using the profile and job requirements obtained from previous tasks, tailor the resume to highlight the most relevant areas."
        "Employ tools to adjust and enhance the resume content."
        "Make sure this is the best resume even but don't make up any information."
        "Update every section, including the initial summary, work experience, skills, and education."
        "All to better reflect the candidate's abilities and how it matches the job posting."
    ),
    expected_output=(
        "An updated resume that effectively highlights the candidate's qualifications and experiences relevant to the job."
    ),
    output_file="tailored_resume.md",
    context=[research_task, profile_task],
    agent=resume_strategist,
    human_feedback=False
)

# Task for Interview Preparer Agent: Develop Interview Materials
interview_preparation_task = Task(
    description=(
        "Create a set of potential interview questions and talking points based on the tailored resume and job requirements. "
        "Utilise tools to generate relevant questions and discussion points."
        "Make sure to use these questions and talking points to help the candidate highlight the main points of the resume and how it matches the job posting."
    ),
    expected_output=(
        "A document containing key questions and talking points that the candidate should prepare for the initial interview."
    ),
    output_file="interview_materials.md",
    context=[research_task, profile_task, resume_strategy_task],
    agent=interview_preparer
)

job_application_crew = Crew(
    agents=[researcher,
            profiler,
            resume_strategist,
            interview_preparer],

    tasks=[research_task,
           profile_task,
           resume_strategy_task,
           interview_preparation_task],

    verbose=True
)

job_application_inputs = {
    'job_posting_url': 'https://amazon.jobs/en/jobs/3102794/sr-ai-ml-consultant-tech-industry-tech-industry',
    'github_url': 'https://github.com/HarshaAsh',
    'personal_writeup': """Harsha Achyuthuni is a seasoned data science professional with over 8 years of experience, currently serving as a Manager at Deloitte. He likes solving complex business problems by integrating data, statistics, technology and business understanding. With a Master's in Business Analytics from Imperial College London and executive education from IIM Bangalore, Harsha has consistently delivered impactful AI and ML solutions across diverse industries, including aerospace, FMCG, pharmaceuticals, insurance, retail, agriculture and manufacturing. His expertise spans predictive maintenance, demand forecasting, optimisation engines, supply chain analytics and cutting-edge generative AI applications."""
}

### this execution will take a few minutes to run
result = job_application_crew.kickoff(inputs=job_application_inputs)

from IPython.display import Markdown, display
display(Markdown("tailored_resume.md"))

display(Markdown("./interview_materials.md"))