Claude
The AI for problem solvers. Built by Anthropic to be safe, accurate, and secure. Talk to Claude on claude.ai or download the app ...
Build a production-ready agent with Claude Managed Agents
The talk introduces Cloud Manage Agents, explains its building blocks and observability, and walks through a hands-on demo showing how to spin up and monitor multi-agent sessions and their environments for production-ready workflows.
The thinking lever
The talk explains how Claude uses test time compute to improve problem solving, outlines different effort levels and model scales, and shares practical guidelines for using thinking, tool calls, and text outputs to balance intelligence, speed, and cost.
Build AI agents using Claude in Microsoft Foundry
The video demonstrates building AI agents with Claude in Microsoft Foundry, covering architecture, hands-on workshop setup, and a live cupcake ordering demo to illustrate agent deployment, tool integration, and MCP driven prompts.
From one person to 80: Scaling a hypergrowth engineering org with Claude Code
The talk describes how Base 44 scaled from a solo founder to about 80 engineers by using simple, automation-driven processes with cloud code, focusing on keeping systems lean and observable. It shares concrete tactics for onboarding, code review, experimentation at scale, and QA to maintain velocity and quality.
What's new in Claude Code
Ralph introduces Entropic cloud code updates focused on improving developer experience and increasing automation, including remote control, full screen terminal, desktop UI refresh, autonomy features, code review automation, routines, and agent views.
Code with Claude London 2026: Opening Keynote
The video presents a keynote on how Claude and Cloud Code are accelerating AI-enabled development, highlighting user stories, platform upgrades, and practical demonstrations of new features like self-hosted sandboxes and MCP tunnels to bridge model capabilities with real-world apps.
Building with Claude Managed Agents and Asana AI teammates
Asana outlines how AI teammates and cloud managed agents enable true multiplayer work within the enterprise, combining shared memory, secure context, and multi-step workflows to execute complex campaigns with human collaboration. The talk also covers pre-built agents, live demos, governance, and future directions for proactive, scalable AI integration.
Running an AI-native engineering org
The speaker discusses how bottlenecks in engineering have shifted from code creation to verification and cross-functional coordination, and shares norms, practices, and metrics Claude Code uses to stay agile and effective as roles blur. The talk ends with practical actions for teams to audit workflows, embrace automation, and continuously re-evaluate what truly serves the team and product goals.
The thinking lever
The talk introduces test time compute for Claude, demonstrates its impact with a traffic simulation example using Opus 4.7, and explains token types, constraints, and the evolution to adaptive thinking and budgets to balance time, cost, and intelligence.
The expanding toolkit
The talk reframes the model as an expanding toolkit where tool use, context management, code execution, and computer use are built into the model, greatly simplifying development and boosting reliability. It uses demos and tips to show practical ways to leverage these capabilities through Claude and Claude Code, with a look ahead to broader agent level front doors for software.
Get daily AI recaps from
Claude in your inbox
Get AI-powered summaries delivered to your inbox. Save hours every week while staying fully informed.