How to integrate LangGraph framework with existing AI chatbot for job interview simulation

Other Questions AI Agent
1

I’m working on a Python app that uses AI to conduct interviews and analyze candidate responses. Right now I have basic functionality working but I want to add LangGraph to make the conversation flow better.

Here’s what my current code looks like:

import os
import random
import openai
from personality_traits import BEHAVIORAL_TRAITS

# Store chat history in a file
def store_chat_log(chat_data):
    file_id = ''.join(random.choices('abcdefghijklmnopqrstuvwxyz0123456789', k=10)) + '.log'
    with open(file_id, 'w') as log_file:
        for message in chat_data:
            if len(message) == 3:  # Context, Query, Answer
                log_file.write(f"Context: {message[0]}\nQuery: {message[1]}\nAnswer: {message[2]}\n\n")
            else:  # Query, Answer
                log_file.write(f"Query: {message[0]}\nAnswer: {message[1]}\n\n")

# Get candidate details at start
def greet_candidate():
    client = openai.OpenAI()
    greeting_prompt = "Create a professional greeting to ask for the candidate's full name. Make it sound natural and welcoming."
    response = client.chat.completions.create(
        model="gpt-3.5-turbo",
        messages=[{"role": "user", "content": greeting_prompt}]
    )
    greeting_text = response.choices[0].message.content
    user_name = input(f"\nInterviewer: {greeting_text}\nYour answer: ").strip()
    print(f"\nInterviewer: Nice to meet you, {user_name}. We'll start with some behavioral questions now.\n")
    return user_name

# Collect responses from candidate
def get_candidate_response(question_text):
    while True:
        answer = input(f"\nInterviewer: {question_text}\n\nYour response: ").strip()
        if answer:
            return answer
        else:
            print("Interviewer: Could you please answer the question?")

# Start the interview process
candidate_name = greet_candidate()
# More interview logic follows here

I’ve tried using CrewAI before and looked into LangGraph but I’m having trouble figuring out how to add it to my existing code. I’m pretty new to these AI frameworks so I’m not sure about the best approach.

What I’ve done so far:

  1. Built basic interview functionality with CrewAI for candidate interaction and conversation logging
  2. Started learning about LangGraph to improve conversation management and decision logic
  3. Created functions for greeting candidates, asking questions, and processing their answers with OpenAI

What I need help with:

  • How to properly add LangGraph to my current setup or if there’s an easier framework to use
  • Best practices for organizing AI agents to handle interview tasks and behavioral assessment

I’d really appreciate any advice from people who have experience with these tools. Thanks for any help you can provide!

2

LangGraph’s probably overkill for this. Your setup already looks solid. If you want to try it anyway, start simple - just build a basic state machine that goes greeting → questions → evaluation. Don’t rewrite everything at once.

3

Your code already handles conversation flow pretty well. LangGraph’s mainly useful for complex branching - like changing questions based on answers or running multiple interview paths at once. I’d stick with what you have but add simple state management. Build an InterviewState class to track where you are (greeting, behavioral, technical, wrap-up) and which questions come next based on responses. The real win would be in behavioral assessment - LangGraph’s great for decision trees where you need to dig deeper or switch question types. But honestly? You’ll probably get more value from better prompt engineering and response analysis before throwing another framework at it.