AI Summary
→ WHAT IT COVERS Anthropic's Code with Claude developer event introduced five updates to Claude Code and the Claude API: scheduled routines, outcome-based agent iteration, multi-agent orchestration up to 25 agents, session memory consolidation called Dreams, and doubled usage limits. → KEY INSIGHTS - **Scheduled Routines:** Claude Code now supports three trigger types—cron schedules, HTTP webhooks, and GitHub webhooks—allowing automated tasks to run locally or in the cloud without manual initiation. Example use case: auto-drafting a customer newsletter every Monday at 6AM from a changelog file. - **Outcomes Framework:** Claude Managed Agents can now self-grade and iterate up to 20 times against a markdown rubric to reach a defined "done" state. Builders upload the rubric via the Files API or inline, then the agent autonomously refines output until it meets the criteria. - **Multi-Agent Orchestration:** The Claude API now supports explicitly defining teams of up to 25 agents sharing a single container and file system. Builders assign one orchestrator role and multiple sub-agents, each with distinct toolsets, enabling parallel workstreams on a single task from different functional perspectives. - **Dreams Memory Consolidation:** A research-preview API primitive lets builders call against a list of past agent sessions—up to 50 or more—triggering a batch review that extracts and writes the most relevant memories to disk on demand, rather than only on session-close hooks. → NOTABLE MOMENT Anthropic's "Dreams" feature replicates how human sleep consolidates memory: the agent reviews past sessions silently and decides what to commit to storage—a framing that reveals how labs are modeling agent cognition on biological processes. 💼 SPONSORS None detected 🏷️ Claude Code, Agentic AI, Multi-Agent Systems, Anthropic API