HireWiz

Transforming recruitment with AI-powered interviews, saving time and reducing hiring costs.

Created on 10th November 2024

•

Problem It Solves:

Time-Consuming Interview Process : Traditional hiring involves multiple interview rounds, scheduling conflicts, and manual assessments, consuming significant time for HR teams.
High Recruitment Costs : Companies incur costs in terms of HR personnel hours, candidate travel expenses, and resources needed for lengthy interview processes.
Limited Access to Quality Talent : Smaller businesses may lack resources to conduct thorough screenings, resulting in missed opportunities for securing top talent.
Inconsistent Interview Evaluations : Human biases and inconsistent criteria can lead to subjective assessments and reduced accuracy in evaluating candidate skills and fit.
Scalability Issues : Growing companies face challenges in scaling interview processes efficiently to match rapid hiring needs without sacrificing quality.
Inefficient Data Management : Manually tracking candidate progress, feedback, and interview data leads to poor data visibility and difficult analysis for HR decision-making.
Candidate Experience Challenges : Slow interview processes and lack of clear communication can result in a poor candidate experience, impacting a company’s reputation.

Challenges We Ran Into:

Integrating Meet Interface Smoothly : Setting up a Meeting interface that allows seamless, interactive communication between the user and the AI was challenging, especially in handling session-based message histories.
Managing Conversation History for Context : Implementing a system to store and retrieve conversation history for context-based responses was complex, especially for maintaining relevance and avoiding repetition.
Testing API Communication : Ensuring reliable communication between the frontend, backend, and AI service through APIs was tricky, as each component had to be tested and debugged for compatibility.
Basic Error Handling : Managing errors like missing inputs, failed API requests, and handling cases where the AI couldn't generate a response presented several debugging challenges.
Response Formatting : Making sure that the AI responses were clear, relevant, and properly formatted required adjusting the prompt and handling formatting issues in the user interface.
Limited Resources and Budget Constraints : Limitations on cloud resources, API usage quotas, and computing power required careful management of resources to stay within budget.
User Feedback Integration : Gathering and interpreting initial feedback to refine the project further was challenging, as it required iterating on small but impactful changes based on real user experiences.

Tracks Applied (1)

Our project uses Streamlit as a user-friendly demo frontend to showcase our AI-HR interview automation solution. By buil...Read More

Major League Hacking

Technologies used

Next.js

WebRTC

Golang

GCP

langchain

gemini

Gen-Ai