🤓 Latest Submissions
MissedCall AI
## MissedCall AI — 24/7 AI Receptionist for Service Businesses Missed calls can mean missed customers, lost appointments, and lost revenue—especially for small clinics and service businesses that cannot afford to have someone answering the phone around the clock. MissedCall AI addresses this problem with an AI-powered voice receptionist that can answer incoming calls, understand what the caller needs, collect important information, schedule appointments, send confirmations, and escalate urgent calls when nexessary. ### How We Built It MissedCall AI is built around real-time voice AI and a lightweight backend designed to be practical for small businesses. * **AssemblyAI Voice Agent API** handles the real-time AI voice interaction. * **Twilio** provides phone-call handling and SMS functionality. * **FastAPI** provides the backend API and application logic. * **SQLite** stores captured caller and appointment information. * **React** powers the administrative dashboard. The system follows a simple flow: a customer calls the business, the AI receptionist answers and collects the required information, the system determines the appropriate action, and the result is recorded in the backend. The dashboard allows staff to view captured calls and leads and monitor the system's activity. ### Key Features * 24/7 AI-powered phone reception * Real-time conversational voice interaction * Lead and caller information capture * Appointment scheduling * SMS appointment confirmations * Urgent-call routing to human staff * Callback handling when staff are unavailable * Call and lead logging * Administrative dashboard * Configurable prompts and business workflows ### Why It Matters The goal of MissedCall AI is not simply to replace a receptionist. It is to make sure that businesses have a reliable first point of contact whenever a customer calls. A business can configure the receptionist around its own services, questions, appointment availability, and escalation rules.
16 Sep 2026
Enclave: Sovereign AI That Never Leaves
Enclave is a sovereign, on-premise multi-agent AI compliance system that runs entirely inside a single AMD Instinct MI300X node, no data ever crosses a network boundary. Banks doing loan underwriting, hospitals processing patient intake, and government agencies reviewing filings need agentic AI, but sending sensitive data to OpenAI or Anthropic's cloud APIs is often a compliance violation before the first token is generated. GDPR, HIPAA, and sovereign-AI mandates require data to stay in a controlled environment. Enclave solves this with a 4-agent pipeline; Orchestrator, Researcher, Analyst, and Auditor, coordinated entirely on one GPU. This is only possible because of the MI300X's large HBM capacity: fitting multi-agent context and shared KV-cache on a single card is the difference between staying fully on-prem versus needing multiple networked GPUs, which breaks the zero-egress guarantee regulators require. We validated this on real AMD Developer Cloud hardware (ROCm 7.2, vLLM 0.16): a full compliance review pipeline ran at 32.8 tok/s with a 14.35 GiB model footprint, and a concurrent 4-agent batched execution proved 1.9x throughput versus isolated cold calls, genuine evidence of single-node concurrent execution, not just an architectural claim. Our auto-tuner enforces the single-node constraint as a hard rule: any configuration requiring a second GPU is automatically rejected, regardless of raw speed, because a network hop between GPUs is a compliance boundary crossed. Enclave turns AMD's memory advantage into a literal compliance advantage, proving that regulated industries no longer have to choose between agentic AI productivity and data sovereignty.
13 Jul 2026
Autonomous Enterprise AI Auditor
Autonomous Enterprise AI Auditor is a multi-agent AI governance and compliance platform designed to help enterprises automatically audit, monitor, and improve their AI systems in real time. As organizations rapidly adopt generative AI and autonomous agents, enterprises face increasing challenges related to compliance, hallucinations, bias, transparency, security, and operational reliability. Our solution addresses these challenges by providing an intelligent auditing layer powered by advanced AI agents running on AMD GPU infrastructure. The platform uses multiple specialized AI agents working collaboratively to analyze enterprise AI systems from different perspectives. A Compliance Agent evaluates outputs against organizational policies and regulatory requirements. A Bias Detection Agent identifies unfair or potentially harmful responses. A Performance & Reliability Agent measures hallucination risks, consistency, latency, and output quality. A Risk Scoring Agent aggregates findings into a unified enterprise risk score with explainable insights and remediation recommendations. The system is powered by open-source Qwen models accelerated with AMD ROCm and AMD GPU infrastructure, enabling scalable and cost-efficient inference for enterprise workloads. Using AMD Developer Cloud and optimized inference pipelines, the platform delivers real-time auditing capabilities suitable for modern AI-powered applications, customer support systems, enterprise copilots, and internal AI agents. Our goal is to build a trustworthy AI auditing framework that helps enterprises confidently deploy AI systems while improving governance, transparency, and operational safety. By combining multi-agent orchestration, explainable AI analysis, and AMD-accelerated infrastructure, Autonomous Enterprise AI Auditor demonstrates how AI can be used to responsibly monitor and govern other AI systems at scale.
10 May 2026
