Realistic HR and recruiter screening practice
Candidates can practise role aware screening conversations through a repeatable telephony workflow.
Internal product case study
AI Voice Screening Platform
Telephony based candidate screening, response capture and interview readiness automation.
Simplify Job Search was developed as an AI powered job application and hiring platform that helps candidates prepare better applications and helps recruiters manage hiring workflows. This case study focuses on the AI Voice Calling Agent, a separate module designed to simulate voice based screening rounds and improve candidate interview readiness.
Project classification: This internal Byond Boundrys product module is part of the Simplify Job Search platform.
Repeatable voice based preparation without another interviewer
The system can place calls and capture responses without requiring another person to conduct each practice round.
Lower anxiety through repeated practice
Repeated practice provides a structured way to prepare before live interviews.
01 / Business context
Who needed the solution
Simplify Job Search was developed as an AI powered job application and hiring platform that helps candidates prepare better applications and helps recruiters manage hiring workflows. This case study focuses on the AI Voice Calling Agent, a separate module designed to simulate voice based screening rounds and improve candidate interview readiness. Modern hiring increasingly includes phone screening, automated first round interviews, recruiter screening calls, and communication based evaluation. Many candidates may have strong technical skills but still struggle to explain their profile confidently in a live voice interaction.
02 / Challenge
What needed to change
Candidates often prepare resumes and job applications but remain underprepared for the first screening conversation. The first recruiter or HR call is usually short, fast, and judgment heavy, and many candidates lose opportunities because they are unable to communicate their value clearly.
Candidates had limited access to realistic phone screen practiceCandidates usually practice written applications but do not get enough realistic voice based interview practice.
Nervousness affected pacing, clarity and confidenceMany candidates are nervous during phone screening rounds and struggle with confidence, pacing, and clarity.
Screening questions were repetitive but still needed personalised responsesHR screening questions are repetitive but still require structured, confident, and personalized responses.
Candidates struggled to introduce their experience effectivelyCandidates often do not know how to introduce themselves, explain experience, discuss strengths, or answer role fit questions in a live call.
Traditional mock interviews required another personTraditional mock interview preparation requires another person, coach, recruiter, or mentor, which may not be available on demand.
03 / Workflow transformation
Before and after
Previous workflow
- Candidates had limited access to realistic phone screen practice
- Nervousness affected pacing, clarity and confidence
- Screening questions were repetitive but still needed personalised responses
- Candidates struggled to introduce their experience effectively
- Traditional mock interviews required another person
Structured workflow
- Unlock and schedule a voice round
- Place the telephony call
- Ask role aware questions
- Capture and review responses
- Review structured outputs
04 / Solution
How we approached it
The Simplify Job Search AI Voice Calling Agent was designed as a voice first interview preparation and screening automation module. Instead of limiting candidates to text based AI outputs, the platform uses calling, real time speech processing, AI generated interview flow, and human like voice responses to create a practical screening experience.
Unlock and schedule a voice round
Manage payment, access and candidate readiness before starting the call.
Place the telephony call
Use a voice workflow to connect with the candidate and manage call state.
Ask role aware questions
Generate or select screening questions using candidate and job context.
Capture and review responses
Transcribe answers, store the interaction and present structured review information.
05 / Example workflow
From input to reviewable output
1Unlock and schedule a voice round
2Place the telephony call
3Ask role aware questions
4Capture and review responses
5Generate review summary
6Candidate or recruiter review
06 / Delivery scope
What the delivery covered
Business and product workflow
- Voice Round Unlock and Payment Flow
- Candidate Practice Call Start Flow
- Asynchronous Queue and Worker Processing
AI, data and automation
- Google Gemini
- Azure OpenAI
Application and cloud engineering
- Angular
- Node.js
- DynamoDB
- AWS
- Docker
- Nginx
Scope boundary
The page covers the implemented voice workflow. Production use requires accurate consent, recording purpose and data retention disclosures.
07 / Architecture and controls
How the system is organised
Google Gemini
Azure OpenAI
Angular
Node.js
DynamoDB
AWS
Twilio
Docker
Candidate consent
Voice calls and recordings require clear consent and purpose disclosure.
Asynchronous reliability
Queue and worker processing separate long running speech and AI tasks from the request flow.
Human review
AI generated summaries support candidate or recruiter review and do not make final hiring decisions.
Operational monitoring
Cloud logging and queue handling support retry, observability and production troubleshooting.
08 / Business value
Value observed during validation
1Pilot observed
Realistic HR and recruiter screening practice
Candidates can practise role aware screening conversations through a repeatable telephony workflow.
2Pilot observed
Repeatable voice based preparation without another interviewer
The system can place calls and capture responses without requiring another person to conduct each practice round.
3Pilot observed
Lower anxiety through repeated practice
Repeated practice provides a structured way to prepare before live interviews.
4Pilot observed
Structured capture of candidate responses
Recorded or transcribed responses can be reviewed after the call.
5Pilot observed
A monetisable AI voice round workflow
Queue based processing supports retry, monitoring and recovery for long running voice tasks.
09 / Technology
Every component, with its role in the delivery.
Technology choices from the supplied project brief, mapped to the workflow each component supports.
Google Gemini
Structured extraction, reasoning or generation
Azure OpenAI
Managed LLM inference and reasoning
Angular
Web application interface
Node.js
Backend and integration services
DynamoDB
Scalable application and workflow data
AWS
Cloud infrastructure and managed services
Twilio
Telephony and voice communication
Docker
Containerised deployment
Nginx
Reverse proxy and production serving
Vertex AI
Managed Gemini and AI model integration
Related work
Explore related case studies.
