Building an AI Interview Preparation Platform, From Credit Economics to Shipped Product
Designed and built an AI-native mock-interview platform end to end: a pay-per-use credit economy verified above 70% gross margin, a dual-model AI pipeline with automatic failover, and a six-axis scored report that grades every answer against an AI-generated benchmark.
About the Project
The First Interview (thefirstinterview.ai) is an AI-native EdTech product helping job seekers, students, and career switchers prepare for real interviews through personalised, AI-generated mock sessions. Rorix owns the build end to end: business model, pricing, AI architecture, and the application itself — session configuration, the scored report, the credit ledger, payments, support, and account management. Sessions are generated from a candidate’s actual job description, resume, or target technology, evaluated against AI-built benchmarks, and monetized through a pay-per-use credit economy instead of subscriptions. The platform is feature-complete and in pre-launch testing.
- Four session modes — resume, skill, job description, and resume + JD — each priced by its real AI compute cost
- Six-axis scored report: readiness, technical, communication, confidence, completeness, relevance, plus per-question AI feedback
- Credit ledger with a running balance, per-axis cost preview, and deduction deferred until the session actually starts
- Gemini Pro 1.5 primary with Claude Sonnet 4 automatic fallback behind a circuit breaker
Challenges We Solved
A Market Split Between Two Broken Models
Existing tools are either static question banks that ignore the role and the candidate, or subscription courses charging monthly for naturally bursty usage. The product had to personalise to a real job description or resume and monetize per use.
Evaluation, Not Just Question Delivery
The value is feedback: every session had to score the candidate’s submitted answers against a benchmark and produce a full performance report, at a cost that stays predictable session to session.
Two Buyer Types From Day One
Individual job seekers buy focused bursts before an interview; colleges and placement cells run mock-interview drives for hundreds of students at once. Both needed first-class flows, not a retrofit.
Volatile AI Costs and Provider Risk
Session cost varies with generation type, difficulty, question count, and behavioral rounds — and a single-provider outage or price change could take the product down or destroy margins.
How We Delivered
Credit Economy Design
Built a granular pay-per-use system where session cost derives from generation type (technology / JD / resume / resume+JD), difficulty, question count, and optional behavioral rounds — pricing that scales precisely with AI compute cost.
Dual-Model AI Architecture
Designed the two-call pipeline (generate questions + internal ideal answers, then evaluate submissions into a report) on Gemini Pro 1.5, with Claude Sonnet 4 as automatic fallback and a circuit breaker protecting against outages.
Margin-Engineered Pricing
Modeled every credit pack and tier against real AI token costs across 60+ session-type combinations, verifying consistent gross margins before a single price was published.
Session Configuration and Cost Preview
Built the setup flow: difficulty, mode, industry, target role, experience level, target skills, question count or a timed session, and technical or behavioral focus — with a live sidebar breaking the cost into mode, difficulty, and volume and showing the balance left after starting.
The Scored Report
Built the evaluation output: six scored axes, a skill breakdown down to sub-skills, key strengths, areas to improve, named skill gaps, an improvement plan, and per-question analysis showing the submitted answer, the correct one, a score, and written AI feedback.
Credit Ledger and Payments
Built the credit system as a ledger with a running balance and overdraft handling, Razorpay checkout over INR credit packs, promo and discount codes, an itemised transaction history, and deduction deferred until the first question so a cancelled session costs nothing.
Account, Settings, and Support
Built the surrounding product surface: Google sign-in alongside email and phone, granular notification preferences including a low-credit alert, light/dark/system theming throughout, password and linked-account management, in-app support tickets, and account deletion.
Institutional Tier and Growth Mechanics
Designed the bulk tier for colleges and training institutes — shared credit pools, per-student caps, an admin dashboard, GST-compliant invoicing — plus signup credits, a first-purchase bonus window, referrals, and streaks, with no subscription lock-in or dark patterns.
Results That Speak for Themselves
Similar Projects
Ready to Build Something Like This?
No fluff. Just a focused conversation about what you're building, what you need, and whether we're the right fit.