An AI Interviewer 🧑🏻‍💻: How We Built an Autonomous Interviewer from 0 → 1 That Reduced Time-to-Hire by 70%

An AI Interviewer 🧑🏻‍💻: How We Built an Autonomous Interviewer from 0 → 1 That Reduced Time-to-Hire by 70%

🔒 This case study is shared while respecting confidentiality agreement. I’ve ensured to keep it engaging while protecting sensitive information. I’ve structured it in chapters outlining the product development journey in brief. This is also how I’ll walk you through it during the case study review (if we get a chance).


A LITTLE CONTEXT: This is the story of how we built a product from 0 → 1 — an AI interviewer that screens candidates and generates detailed analysis reports along with recommendations on who’s actually worth interviewing. This reduced time-to-hire by 70%, saved team's effort, and reduced biasness in hiring.

CHAPTER 1: THE PIVOT

We initially built an L&D and Performance Management platform but later pivoted to recruitment — specifically, building an AI interviewer. This chapter explains why we pivoted, and the factors behind that decision.

CHAPTER 2: THE RECRUITMENT INDUSTRY, LIFECYCLE AND MARKET GAP

Together with the PM, I conducted generative research to understand:

  • The recruitment industry,

  • Recruitment workflows,

  • Competitor landscape,

  • Gaps in the market (especially in the GenAI era).

CHAPTER 3: TROJAN HORSE METHOD OF RESEARCHING B2B PLATFORMS

We explored the full landscape, from legacy platforms to new-age AI-first platforms. Here, I also describe an unconventional (arguably non-traditional, but highly effective) method of researching B2B competitors that goes beyond standard secondary research.

CHAPTER 4: PRODUCT PLANNING, MVP, AND MARKET ENTRY

The entire team worked together to define:

  • Focus areas,

  • MVP scope,

  • Tech stack (frontend, backend),

  • UI libraries to be used (I contributed to this decision too).

CHAPTER 5: TECHNICAL RESEARCH, INTEGRATION AND EARLY FAILURES

This part covers my research on ATS API integration — why we struggled to achieve our goal that we had early on, and whether we were simply too early in our approach.

CHAPTER 6: B2B PARTNERSHIP TALKS AND EARLY DEMOS

We began showcasing our product to companies like ANSR, engaging in partnership/acquisition conversations. The product was only partially functional — we demoed the rest via Figma prototypes. The feedback was positive and gave prospective partners clarity on our vision.

MILESTONE: SUCCESSFULLY ACHIEVING THE “VALUE LOOP”

We built a functioning product (UI was terrible, but that wasn’t the point). What mattered was delivering value:

  • The AI could autonomously interview candidates,

  • Assess their suitability based on the JD, resume, and interview responses,

  • Generate reports recommending whether they should proceed to the next round.

CHAPTER 8: BUGS & BREAKDOWN – TECHNICAL & UX CHALLENGES

We faced major technical issues:

  • AI agents would randomly stop asking questions,

  • Mic picked up background noise,

  • The website hanging & freezing,

  • Screen and video recordings failing.

We solved some of these by tweaking the UX, e.g., dynamically adjusting mic sensitivity in real time. This phase taught me that building AI products is 80% technical problem-solving. UX was important but secondary at this point.

MILESTONE: SCREENING 100+ CANDIDATES, REAL-WORLD TESTING

We screened over 100 candidates across multiple roles for internal hiring. We recorded all interviews and monitored sessions via LogRocket for both technical and behavioral analysis.


Interesting learning: Candidates often felt confused or overwhelmed by interacting with an AI interviewer — this was new territory for them. The large-scale testing gave us clear technical and UX problem areas to prioritize.

CHAPTER 10: RESEARCH PHASE 2 – INTERVIEWING HR LEADERS, CHROS, RECRUITMENT MANAGERS FROM STAFFING & RECRUITMENT FIRMS

We spoke to:

  • HR leaders, CXOs of staffing agencies (our ideal customers),

  • Learned how recruitment is evolving with AI,

  • Secured interest from early adopters and innovators willing to try our product.

CHAPTER 11: SOLVING DEEPER TECHNICAL ISSUES, RESEARCH & TESTING AND WHY WE HAD PRIORITIZATION PROBLEM

Remember the temporary mic-fix in Chapter 7? We wanted more human-like conversations — our AI still sounded robotic and sequential.

We evaluated tools like Vapi, ElevenLabs, Synthflow, testing extensively to create natural-sounding AI interviews. Integration improved conversation quality significantly while resolving several technical issues simultaneously.

CHAPTER 12: CURRENT STATUS - GTM STRATEGY PHASE

We’re currently:

  • In partnership conversations with recruitment firms (our ideal ICPs),

  • Continuously using the product internally,

  • Preparing for broader go-to-market execution.

Convincing? Let's connect for a deep dive of the Product.

Convincing? Let's connect for a deep dive of the Product.

Copy my email

Copied

Copy my email

Copied