Where developers grow together

SentinelAI — Real-Time AI Incident Commander

SentinelAI is a real-time conversational AI incident commander designed to help technical teams coordinate during live operational incidents. It joins an Agora-powered voice room as an active AI participant, listens to the conversation, understands participant roles, and continuously builds a structured Live Incident State. SentinelAI separates confirmed facts from hypotheses, tracks decisions, actions and ownership, detects missing or conflicting information, maintains a live incident timeline, and surfaces unresolved risks. It can provide spoken status updates and clarification requests while keeping humans in control of critical actions through explicit approval. The prototype demonstrates how real-time voice communication, conversational AI, and AI-agent intelligence can work together to create faster, safer, and more accountable incident response.

RuleGit

This project tries to present goverment act, rules, policies, SOPs in versioned structure. Each of the modifying notification, circular or even clarifying instruction bumps the version.    As the name suggests, it is git but for rules. It has functionality to compare different versions, see what individual instructions added, deleted, modified which paragraph or section of policy. With this the visitors are able to see the policy rules existing at any point of time

AI-Powered Voice Interviewr And Coach

InterviewIQ is an enterprise-grade, AI-adaptive voice interviewing platform that transforms how companies conduct and evaluate technical interviews at scale. Today, technical hiring is broken: interviews are inconsistent across candidates, feedback is subjective, senior engineers waste hours on first-round screens, and there is no auditable evidence trail behind hiring decisions. Companies face legal risk, bad hires, and scheduling bottlenecks. InterviewIQ solves this by deploying an AI interviewer that conducts natural, real-time voice conversations with candidates while running a deterministic intelligence engine behind every interaction. The system extracts verified competency evidence from candidate responses, selects each follow-up question based on the largest remaining evidence gap, and validates every question through a 5-point reliability gate (format, relevance, repetition, latency, and quality) before it reaches the candidate. An anti-hallucination guard ensures no fabricated quotes ever enter the evaluation. Recruiters get a live dashboard during the interview and a frozen, auditable scorecard at the end with competency scores, verbatim candidate quotes, question audit trails, and evidence-backed hiring recommendations. Every decision is transparent, consistent, and defensible.