All Engineering
Engineering
Selecting a text-to-speech (TTS) voice – the voice someone speaking with an AI agent hears – sounds simple: generate a few samples, listen to them, and choose the one everyone likes. We learned quickly that this approach does not work for production systems, especially in healthcare. A voice can sound warm in a demo while...
Voice AI has a latency problem: users expect instant responses, but hallucination checks can take seconds. In real-time conversation, adding a verification step before speech often makes an AI agent feel slow and unnatural. GhostEdit – a real-time safety layer we built at Infinitus that checks each spoken AI response against grounded knowledge and triggers...
In AI evaluation, pass@k measures capability: given k attempts, what is the probability that at least one output is correct? For example, imagine an AI generating prior authorization summaries. If the model produces five variations and at least one meets the desired result, that counts as a success. If this happens in 92 out of...
Adverse event (AE) detection is vital for pharmacovigilance and regulatory compliance. To address this need, Infinitus developed SAGE, a robust NLP system that detects AEs using a human-in-the-loop approach. While LLMs are exceptional at identifying potential events, their broad contextual awareness often introduces noise, misinterpreting unrelated phrases as safety concerns. To solve this, we leverage...
For years, technical interviews have relied heavily on LeetCode-style problems: algorithms, data structures, and whiteboard puzzles. While these can test pattern recognition and persistence, they rarely reflect the realities of day-to-day engineering. The gap between “acing the interview” and “thriving in the role” has grown too wide. Attracting and hiring great engineers requires a better...
In addition to our patient-facing and provider-facing agents, we have voice AI agents that call payors on behalf of healthcare providers to collect detailed patient benefits and prior authorization data. On these long and complex phone calls, our AI agents operate on a multi-modal, multi-model platform adhering to each customer’s unique standard operating procedures (SOPs)...
Automating benefit verification phone calls saves time in healthcare and helps patients receive treatment faster. It is critical to obtain highly accurate information in these phone calls because it can affect a patient’s healthcare journey. However, it is also very difficult to extract all the required information from real-time streaming speech-to-text (STT) models with high...
As the use of agentic AI systems accelerates across industries, particularly in healthcare, it becomes essential to understand the infrastructure and protocols that enable scalable, modular, and interoperable agent-based ecosystems. Two key enablers in this space are the Model Context Protocol (MCP) and the Agent2Agent (A2A) protocol. While each serves a distinct purpose, their complementary...
At Infinitus, our voice AI agents can call payors on behalf of healthcare providers to collect detailed patient benefits and prior authorization data. These calls are complex and lengthy (often over an hour), and require navigation through convoluted IVRs, long hold times, and transfers to human representatives. Our AI agents operate on a multimodal, multi-model...
We often speak about the importance of humans in the loop in AI, and how Infinitus uses humans in concert with our purpose-built AI system. Our human experts serve a number of roles in our ecosystem, including stepping into live calls the Infinitus AI agent is conducting with payor representatives. This may occur if the...
Our customers have referred to Infinitus voice AI agents as the best performers on their team. And while these AI agents may seem like magic to the payor representatives, patients, and providers they speak to, it is in fact the Infinitus knowledge graph that powers much of the agents’ capabilities. Those capabilities are anything but...
How we use humans in concert with our multi-model, multimodal AI system to deliver real efficiency to over a dozen Fortune 500 healthcare customers Automating administrative phone calls in healthcare is no easy feat. The benefit verifications and prior authorization inquiries Infinitus automates can be an hour long, with hundreds of back-and-forth interactions that require...
Recently there have been huge advancements in the ability of large language models (LLMs) to handle conversational systems. In many practical industry settings, the conversational AI systems we want to build are task-oriented dialog systems (TODs). In these systems, the goal is to help a user complete a task or collect certain information. For many...
