geon park@losblancos339

SecondLine gives individuals a short way to rehearse a safe pause before an urgent request for a one-time code or payment. In a clearly fictional English scenario, an agent built on the AssemblyAI Voice Agent API speaks one pressure line. The learner answers aloud with a boundary and explains how they would verify the claim through an official app or contact route found independently. The browser shows the final transcript turns from that exercise. A deterministic reflection quotes captured pressure words, highlights only practice steps supported by the learner's response, and suggests a next try. It does not score the caller or decide whether a real request is genuine. The API key stays on the server; the browser uses a short-lived token. The public prototype uses real AssemblyAI voice infrastructure and has completed a synthetic browser-microphone test. SecondLine never joins a real call, contacts an institution, requests an actual code, or moves money. Financial-literacy educators could use short exercises like this to help learners practice a response in their own words. That is a use hypothesis: we have not measured learning outcomes, fraud prevention, or real adoption.

🌎 Online Hackathon | 💻 Month-long challenge | Dates: Sep 1–30, 2026 | 🏆 $10,000 Prize Pool ($5k cash + $5k in AAI credits) A month-long online challenge run by lablab.ai together with AssemblyAI, the Voice AI infrastructure company for builders. Every participant builds on AssemblyAI. You can join at any point — registration stays open for the whole build window, so you can start on day one or pick the project up halfway through and still submit. 🌍 Fully online hackathon. Join and build from anywhere in the world.