AI Agents Podcast

James Luan, Co-founder and VP of Engineering at Zilliz, who helped build Milvus and vector database infrastructure. He explains why vector databases are central to modern AI, how retrieval augments LLMs, and the mechanics behind RAG, hallucinations, and long-term memory for agents. He also discusses scaling production-grade systems, MCP as a tool layer, and practical developer productivity wins.

Dror Asaf, Co-founder and CTO of Coval, a veteran in enterprise AI and supply chain automation. He discusses bringing agentic AI into operations, why supply chains remain archaic, trust and security hurdles, on‑prem and Teams integrations, governance for compliance, and how AI will reshape jobs toward decision‑making rather than replacement.

David Wong, Chief Product Officer at Thomson Reuters, drives product and AI strategy for legal, tax, audit, and accounting software. He talks about how AI has evolved for legal research and document work. They explore AI automating tax prep and compliance. He outlines building professional AI agents using tools, authoritative data, and practitioner training.

Brian Raymond, founder and CEO of Unstructured, builds tooling that turns messy enterprise files into GenAI-ready formats. He discusses why structured inputs like JSON and HTML matter, the persistent challenges of tables and scanned docs, and how preprocessed data can power more reliable agentic systems. The conversation also covers practical industry use cases and what enterprise AI needs to move prototypes into production.

Aytekin Tank, CEO and founder of Jotform, a longtime product leader, describes using Claude Code to rebuild five abandoned sites and deploy them without writing code. He talks about running multiple parallel AI coding sessions, integrating deployments with Vercel and GitHub, live demos of plan-driven edits, and how AI shifts the bottleneck from implementation to ideas and product taste.

They explore a powerful always-on AI that can control a computer, run recurring workflows, and generate reports and Keynote decks. A live demo shows fetching reviews and turning them into polished outputs. They debate agent teams, autonomous 24/7 operation via messaging apps, and the security tradeoffs of giving agents deep access.

They explore “vibe working” and how parallel AI agents change knowledge work and productivity. They discuss agent teams, agent stress, and running digital workers like human teams. They compare Claude, GPT, and Gemini and unpack token economics and subsidized plans. They demo building motion graphics, ad dashboards, research systems, and internal tools with natural-language programming.

Max Eisendrath, Founder and CEO of Red Flag AI, builds large-scale content protection and anti-piracy tools for creators and publishers. He explains how piracy has shifted to live leaks and evasive edits. He breaks down watermarking, fingerprinting, provenance tracking, and the Red Flag Shield idea to make model training costly. He discusses cross-platform protection and recovering lost creator revenue.

Kevin White, Head of Marketing at Scrunch, helps companies measure and optimize brand visibility for AI-driven discovery. He discusses benchmarking presence across LLMs, detecting AI crawler traffic, optimizing sites with bot-friendly formats like markdown/JSON, and creating separate experiences for bots and humans. The conversation highlights trends like zero-click search and how AI surfaces long-tail opportunities.

David Petrou, founder and CEO of Continua AI and former Google AI researcher, builds social AI that helps groups collaborate. He discusses agentic systems that join group chats, multimodal advances, and designing polite, memory-enabled chat participants. The conversation covers real-world demos, on-device vs cloud tradeoffs, and practical use cases like trip planning and team coordination.