Home
Speaker
Ishan Bhatt

Ishan Bhatt

AI Systems Engineer at Microsoft | Creator of Crucix (10k Github⭐) and OpenMontage (35k Github⭐) | Builder of Agentic Systems

Bio

Ishan Bhatt is an AI Systems Engineer at Microsoft and creator of several widely adopted open-source AI projects with more than 45,000 GitHub stars. His work focuses on building autonomous systems that move beyond code generation into real-world execution across intelligence gathering, content creation, enterprise operations, and financial markets. Over the past 14+ years, Ishan has built large-scale distributed systems at Microsoft, Cloudera, Oracle, and Cognizant. Today, he specializes in agentic architectures, multi-agent orchestration, autonomous workflows, and AI-powered decision systems deployed in production environments. At Microsoft, he has led initiatives spanning autonomous monitoring, AI-powered incident response, executive intelligence systems, and next-generation reconciliation platforms. Outside of work, he builds in public and is the creator of Crucix, an AI-powered intelligence platform, OpenMontage, an autonomous video production engine, and several other open-source AI systems used by developers and creators worldwide. His talks focus on practical lessons from building real-world AI systems, helping engineers understand how AI can become a harness for creating products, workflows, and businesses that previously required entire teams.

Talk

18:00 – 18:45NexusNexus

Video Production Is an Orchestration Problem: Lessons From a 34,000-Star Open-Source Agentic System

Most agentic AI aims at developers. This talk points it at work with no developers at all — producing video — and treats it as what it really is: an orchestration problem. OpenMontage is an open-source multi-agent system (12 pipelines, 52 tools, 34,000+ GitHub stars) that turns a single prompt into a finished, edited video. I'll go past the demo into the architecture that makes autonomy reliable: single-responsibility "stage director" agents coordinating through a durable artifact-and-checkpoint contract on disk instead of fragile conversation state. I'll be honest about what didn't work — the mega-prompt monolith, coordinating agents through chat history — and why each failed, then take a real run from prompt to finished video live on stage. You'll leave with a concrete, reusable blueprint for orchestrating multi-stage agentic work in your own domain, developer or not.

intermediateIngleseTalk + DemoAgentic AIGenerative AI