Arjun

Serving Voice AI at Scale — Arjun Desai (Cartesia) & Rohit Talluri (AWS)

Jun 27, 2025 · 17:05

Arjun Desai of Cartesia AI and AWS's Rohit Talluri discuss scaling voice AI for enterprise, arguing that latency and controllability are critical, with Cartesia's state-space model Sonic 2 achieving 40ms model latency for real-time applications. Desai explains that traditional transformer models scale quadratically, while Cartesia's SSMs maintain O(1) generation, enabling 2.5x faster inference than their earlier models. He emphasizes that edge deployment is 5x faster than cloud round-trips, making local models essential for interactive use cases. On quality, Desai notes that voice AI must handle interruptions, accents, and background noise, and that Cartesia's voice marketplace amplifies human voice actors rather than replacing them. Looking to 2030, he predicts voice AI will become the default interface across healthcare, customer support, and gaming, with interactive models extending beyond audio to full world models.

Beyond APIs: How AI Web Agents Are Automating the "Long Tail" of Knowledge Work

Feb 22, 2025 · 17:44

Arjun and Bhavani present Rtrvr.ai, a universal AI web agent using a text-based approach to autonomously perform tasks across multiple browser tabs at under a penny per page. They argue text-based reduces hallucination compared to vision-based agents like OpenAI's operator, and being a Chrome extension avoids password sharing and accesses logged-in content. Features include deep research navigating multiple pages, dynamic function calling for any third-party API, and graph generation. Rtrvr extracts structured data, performs actions like clicking dropdowns, and processes tabs simultaneously, automating the long tail of knowledge work including market research, LinkedIn automation, and WhatsApp messaging. They claim a distributed subtask approach lowers failure rates and envision collaborative dataset construction, e.g., aggregating local government events.

What It Actually Takes to Deploy GenAI Applications to Enterprises: Arjun Bansal and Trey Doig

Nov 4, 2024 · 21:30

Trey Doig of Echo AI and Arjun Bansal of Log10 recount Echo AI's journey deploying a GenAI-native conversational intelligence platform for billion-dollar retail brands, focusing on the centrality of accuracy. Echo AI ingests all customer conversations, uses LLMs to surface insights at 100% coverage, but must overcome enterprise trust issues by achieving 95% accuracy within seven days. The platform relies on Log10's auto feedback system, which uses AI-based review to match human accuracy with model speed, yielding a 20 F1 point improvement in one use case. The episode details how Echo AI's solution engineers use Log10 to grade summarizations, catch hallucinations, and track model drift, turning human feedback into curated datasets for fine-tuning. Ultimately, the partnership demonstrates a path to self-improving LLM applications through iterative accuracy measurement and improvement.