Barr Yaon of Amplify Partners presents early findings from the 2025 State of AI Engineering survey, covering LLM usage, customization techniques like RAG and fine-tuning, the state of AI agents, key challenges like evaluation, and community perspectives on the future of AI.
A deep dive into the design principles for building effective AI agents, covering the evolution of the ReAct loop, the critical role of memory and learning from experience, the 'build vs. buy' dilemma for tooling, and the importance of abstracting all capabilities—including systems and people—as tools.
Anthropic executives and financial industry leaders from S&P Global, Deloitte, DE Shaw, HG Capital, New York Life, and the Norwegian Sovereign Wealth Fund discuss the future of AI in finance and announce Claude for Financial Analysis, a unified intelligence layer designed to transform professional workflows.
A deep dive into the challenges of building production-grade, low-latency voice AI agents, and how the open-source, vendor-neutral framework Pipecat provides a comprehensive solution for development, deployment, and scaling. Learn about voice AI architecture, the trade-offs between speech-to-speech and text-based models, and practical deployment strategies.
In a presentation from Code w/ Claude, AWS advocates Du'An Lightfoot, Suman Debnath, and Banjo Obayami introduce Strands, a new open-source Python SDK for building AI agentic applications on AWS. They showcase how Strands simplifies development by focusing on three core components—models, tools, and prompts—and leverages the full reasoning power of foundation models like Claude 3.5 on Amazon Bedrock. The session includes live demos on creating a multi-tool weather agent, integrating with Modular Connected Protocol (MCP) servers for AWS documentation and diagram generation, and using Claude Code to auto-generate a complete Strands agent for AWS CDK.
Ivan Nardini from Google Cloud demonstrates how to build, enhance, and productionalize AI agents using Google Cloud's agent stack. The session covers the challenges of deploying agents and introduces the Agent Development Kit (ADK) for building, the Vertex AI Agent Engine for managed deployment, and protocols like MCP and Agent-to-Agent for tool integration and inter-agent communication, using Claude on Vertex AI as the core LLM.