Where developers grow together

Sentinel- An AI Incident Commander

Sentinel is an AI Incident Commander that transforms real-time incident conversations into structured, evidence-backed intelligence. It uses Agora-powered voice communication, a Truth Engine to distinguish facts, hypotheses, conflicts and unknowns, and human-in-the-loop approvals for risky actions. Our goal is to reduce incident-response complexity, accelerate decision-making, and help engineering teams resolve critical incidents safely and efficiently.

Probe

Project Purpose & Goals PROBE is an AI-powered mock interview platform designed to simulate a realistic, three-person panel interview in real time. Rather than relying on rigid, pre-written scripts, it uses a central orchestrator powered by Google Gemini to analyze your responses on the fly. Every few seconds, the system determines which panelist should speak, what area needs further exploration, and how to challenge you next. The simulated panel covers three key perspectives to mirror a real tech or corporate interview. Abhinav serves as the Technical Interviewer focusing on system architecture, code correctness, and trade-offs. Anisha acts as the Product Manager probing user impact and business metrics. Alia handles the Hiring Manager role, evaluating leadership, collaboration, and communication. The platform pairs this dynamic conversation with animated 3D avatars, real-time speech processing, and built-in proctoring tools to maintain an authentic testing environment. After completing a session, users receive a detailed assessment report scoring their performance across five core competencies: technical ability, problem solving, product thinking, leadership, and communication. Additional features include resume analysis against job descriptions, a personal question bank for review, and progress tracking over time. Available on a free tier or a subscription plan for unlimited access, PROBE caters to job seekers looking for low-pressure practice, bootcamps managing student preparation at scale, and enterprise recruiters seeking automated candidate screening.

SahaayaAI — AI That Knows When to Ask for Help

SahaayaAI is a multilingual, real-time voice AI assistance agent designed for difficult customer-support and public-information conversations. Real callers may switch between languages, speak through background noise, interrupt the agent, or provide incomplete information. In these situations, simply generating a confident answer is not enough — the AI must know when it is uncertain. SahaayaAI follows a five-stage operating loop: Understand → Collect → Confirm → Assess → Escalate. It identifies the caller's intent and essential details such as location and service identifiers, while maintaining field-level confidence. When a critical detail is unclear, SahaayaAI does not guess. It asks for confirmation and, if uncertainty remains, escalates the conversation to a human with the relevant transcript, confirmed information, missing information, confidence indicators, and reason for escalation. The prototype demonstrates Hindi + English code-switching, noisy-call handling, interruption awareness, confidence-aware decision making, critical-detail confirmation, and human-in-the-loop escalation using real-time voice communication. Our core principle is simple: AI handles the conversation. Humans handle the decisions. SahaayaAI is designed not to replace human support agents, but to handle the conversation safely until human judgment is needed.