Multi agent systems

Jun 18, 2026

The Production AI Playbook: Deploying Agents at Enterprise Scale — Sandipan Bhaumik, Databricks

Sandipan Bhaumik presents a five-pillar framework for successfully moving AI systems from demos to production, inspired by a retail bank's failed chatbot PoC. The framework covers defining numerical success (Evaluation), tracing every AI decision (Observability), building robust data pipelines (Data Foundation), managing multiple AI interactions (Multi-agent Orchestration), and ensuring accountability and security (Governance). He illustrates these concepts with a banking chatbot case study, emphasizing continuous evaluation, data quality, and a proactive incident playbook.

Jun 09, 2026

Building AI Agent Systems and Scaling Challenges in Agentic AI

Scaling agentic AI systems presents unique challenges beyond traditional software scaling. This summary explains why expanding a single agent's capabilities leads to non-linear increases in cost, latency, and failure propagation. The talk frames this as a systems design problem solved by moving from a monolithic agent to a multi-agent architecture with distributed responsibilities, and it explores the critical architectural trade-offs between horizontal and vertical scaling of agent capabilities.

May 25, 2026

Scaling Meta's Multi-Agent Systems to a Billion Videos

Meta's approach to solving modality misalignment and content theft in short-form video using a multi-agent system of smaller, specialized models instead of a single large LLM. The talk covers the architecture (Perceiver, Retriever, Reasoner), evaluation stack, and key cost-saving optimizations.

May 24, 2026

Scaling the Next Paradigm of Heterogeneous Intelligence — Adrian Bertagnoli, Callosum

Adrian Bertagnoli from Callosum argues that the era of scaling monolithic models on homogeneous GPU clusters is ending. He introduces "heterogeneous intelligence," a new paradigm where model architectures, chip types, and workflows are optimized together. By routing subtasks to the most efficient model and hardware, this approach achieves significant performance gains, as demonstrated by two key results: a 7x cost reduction in recursive reasoning tasks using Cerebras, and state-of-the-art performance on the Video Web Arena benchmark, outperforming leading GPT and Gemini models at a fraction of the cost and time.

May 18, 2026

MCP vs ADK: How Modern AI Agents Connect and Work Together

AI agents are having a moment, and understanding MCP and ADK is key to building them well. Cedric Clyburn and Anna Gutowska explain how MCP powers tool integration while ADK structures reliable multi‑agent systems 🤖. Learn when to use each to build more capable and predictable AI agents.

May 11, 2026

Viktor: AI Coworker That Lives in Slack — Fryderyk Wiatrowski

This talk explores the journey of building Viktor, an AI employee that lives entirely in Slack. It details the unique challenges of scaling an AI agent from a personal tool to a company-wide coworker, focusing on memory isolation, context management across different Slack interactions (DMs, channels, threads), and the surprising importance of the AI's personality for user adoption.