Code w/ Claude SF 2026: Building on the AI exponential

2026-05-12 · Source: Claude Blog · Field: Technology & Digital — Artificial Intelligence & Machine Learning, Software Development & Engineering, Cloud Computing & IT Infrastructure · Depth: Advanced, quick

Summary

Anthropic recently hosted "Code w/ Claude SF 2026," its annual developer conference in San Francisco, bringing together developers, engineers, and founders. The event focused on the accelerating pace from idea to production software, emphasizing designing for the "AI exponential." Key announcements included doubling rate limits for Claude Code and raising API limits for Claude Opus to support scalable development. Additionally, new capabilities were introduced to Claude Managed Agents, including "Dreaming" for scheduled memory curation, "Multiagent orchestration" for parallel subagent delegation, "Outcomes" for rubric-based result evaluation (improving task success by up to 10 points on hard problems), and "Webhooks" for outcome notifications. Session recordings are available on YouTube, and future conferences are scheduled for London (May 19-18) and Tokyo (June 5-6).

Key takeaway

For AI Architects and VP of Engineering overseeing AI-native teams, the enhanced Claude API limits and new Managed Agent features offer significant scaling and reliability improvements. You should explore integrating "Dreaming" and "Outcomes" into your agent workflows to improve performance and automate quality assurance, potentially boosting task success by up to 10 points. Consider attending upcoming Code w/ Claude events in London or Tokyo for deeper technical insights.

Key insights

Designing for the AI exponential narrows the gap between idea and production software.

Principles

• AI agents improve through scheduled memory curation.
• Delegation to specialist subagents enhances complex task execution.

Method

Claude Managed Agents use Dreaming for memory, multiagent orchestration for parallel tasks, Outcomes for rubric-based evaluation, and Webhooks for notifications.

In practice

• Utilize doubled rate limits for Claude Code and Opus APIs.
• Implement Claude Managed Agents for scalable cloud-hosted agent deployment.

Topics

• Claude
• AI-native Engineering
• Managed Agents
• Multiagent Orchestration
• API Limits

Best for: CTO, AI Architect, VP of Engineering/Data, AI Engineer, MLOps Engineer, Director of AI/ML

Related on AIssential

• New in Claude Managed Agents: dreaming, outcomes, and multiagent orchestration — New Claude Managed Agents features enable self-improving, outcome-driven, and complex multiagent task execution.
• 4 New Techniques to Maximize Claude Code — Optimizing coding agent interaction through specific techniques significantly boosts developer productivity and output quality.
• v2.1.56 — Claude Code updates focus on performance, security, and extensibility, enhancing developer workflows and multi-agent capabilities.
• Claude's New "Infinite" Context Window Model, Doubled Rate Limits, Multi-Agent Cordination, & More! — Enthropic is advancing Claude towards autonomous software engineering with enhanced agent intelligence and increased compute capacity.
• TAI #186: Claude Code and the Christmas Awakening: Why CLI Agents Are Winning the Agentic Race — Agentic AI tools with file system access are driving significant productivity gains for both technical and non-technical users.
• Claude Code 2.0 MASSIVE Upgrade! (Game Changer) — Claude Code's latest updates enhance developer productivity through improved scheduling, memory, and multi-agent capabilities.

Open in AIssential →

Editorial summary, takeaway, and curation by AIssential. Original article published by Claude Blog.