Voice AI Buildathon: Build an AI That Can Interview

Paytm × AI Garage | Bengaluru | 17 October 2026 Most Voice AI demos stop at having a conversation. In this buildathon, we’ll go one step further: build Voice AI agents that interview people, understand what they’re saying, and turn conversations into useful structured outcomes. We’ll start with a walkthrough of a real AI hiring automation built by AI Garage. Then, you’ll choose one of two challenges and build your own interviewer agent. No slide-deck hackathon. We end with working demos. Part 1 | Host Walkthrough: AI Hiring Automation We’ll start by breaking down a real workflow: Candidate applies → AI voice agent calls → conducts screening interview → transcript is evaluated → structured candidate data is generated → next action is triggered We’ll look at how the different pieces work together: Voice AIconversational promptingfollow-up questionsstructured data extractionLLM evaluationworkflow automationhuman reviewdownstream actions The goal isn’t to copy the hiring use case. It’s to understand the primitives well enough to build your own interviewer agent. Part 2 | Buildathon Choose one of two challenges. Challenge 1: Personal Interviewer Agent What if you never had to fill another application form manually? Build an agent that can take an application/form, understand what information is required, and interview the user over voice to produce the answers. For example: Application/Form → Agent understands questions → Voice interview → Follow-up questions → Draft answers → User review The agent shouldn’t simply read every form field aloud. A strong agent should understand what information is missing and probe for better answers. If a form asks: Tell us about something you've built. The agent might ask: What exactly did you build?What part did you personally own?Who used it?What happened as a result?Is there a number or outcome we can include? At the end, the user should receive a structured draft ready for review. Human approval stays in the loop before anything is submitted. Challenge 2: Problem Intake Agent Real problems are usually trapped inside messy conversations. Companies, founders and individuals often have useful problems for builders to solve but turning those problems into a clear brief requires multiple calls, messages and follow-ups. Build an AI interviewer that does that work. The agent should interview a problem giver and progressively understand: What is happening today?Who experiences the problem?How is it currently being solved?Why does it matter?How frequently does it happen?What constraints exist?What has already been attempted?What information is confidential?What would a useful outcome look like? The agent should ask follow-up questions instead of simply completing a questionnaire. At the end, convert the interview into a structured problem brief that another builder could understand and start investigating. Bonus points if your agent can: identify missing informationseparate facts from assumptionsdetect sensitive/confidential informationhelp the problem giver redact detailscreate different versions of the brief for different audiences Think of it as: Real person/company → AI interview → clarified problem → structured brief → ready for builders What You'll Build With Use whatever stack helps you ship. You may work with tools such as: Voice AI + LLMs + n8n/automation + forms + databases + browser agents + your preferred APIs. Teams are encouraged to use AI coding tools. This isn't a competition to write the most code. It's a competition to build the most convincing working agent. Final Demos At the end, teams will demo their agents live. We care about: Does it actually work?Does it conduct a good interview?Does it ask intelligent follow-ups?Does it produce a useful output from the conversation?Can someone realistically use this after the event? Expect your agent to be tested with inputs it hasn't seen before. Who Should Join? Builders, developers, product folks, automation enthusiasts, founders and anyone experimenting with AI agents. You don't need to be a Voice AI expert. But you should be comfortable building things and be ready to spend most of the event actually shipping. Bring your laptop. Come with curiosity. Leave with an agent that can interview. ​Community Partner: Paytm We’re excited to have Paytm as the community partner for this session. Paytm is one of India’s leading digital payments and financial services platforms, building products used by millions of consumers and businesses across the country. A great partner to have as we help non-tech folks become AI builders, marketers & operators.