Build a Research Agent with Claude Managed Agents (Part 2 of 4) — Anthropic

Why watch

Build a research agent using Claude Managed Agents with skills, subagents, shared memory, and self-grading outcomes. Demonstrates building a chat UI, adding an SEC EDGAR skill, implementing a grader that evaluates Claude's work against a rubric and triggers retries, and managing secrets with vaults. Ideal for developers building production AI agents.