CLAUDE May 8, 2026

Code with Claude 2026: 5 New Agent Features Anthropic Just Shipped

WHAT CHANGED

Anthropic held Code with Claude developer events in SF, London, and Tokyo. No new models — instead, 5 production-focused agent features shipped: Dreaming (background reasoning during idle time), Outcomes (evaluable goals not just completions), multi-agent orchestration with manager+worker patterns, Claude Finance with 10 pre-built finance agents, and Add-ins (deeper Microsoft Office integration).

WHY IT MATTERS

The frontier model race has quieted relative to the harness race. Codex vs Claude Code is now a more meaningful contest than GPT vs Opus. These 5 features are Anthropic's answer to: what does the scaffolding around a capable model need to do? Manager+worker agent teams + 18+ hook types + multi-agent orchestration = production-ready agent stacks.

HOW TO USE IT

Update Claude Code to the latest version. /dream enables background reasoning. /outcomes lets you define success criteria. multi-agent: a manager agent delegates to parallel workers — check anthropic.com/docs/claude-code/agents for setup.

CLAUDE / BASH

# 3-agent team that builds a full site in parallel
claude --agent-team "manager,frontend,backend" \
  "Build a SaaS landing page with auth, billing, dashboard"

anthropicclaude-codeagentsdreamingoutcomes

ORIGINAL SOURCE

https://www.mindstudio.ai/blog/code-with-claude-2026-new-agent-features

VIEW ORIGINAL SOURCE →

Anthropic held no model releases at the event. That was deliberate — the bottleneck for most production agents isn’t model capability, it’s the infrastructure around the model. Customer talks featured Asana, Cursor, GitHub, Replit, and Vercel. The Tokyo event extends to June 5-6.

← BACK TO UPDATES