The Video Signal

Topic

Claude Managed Agents docs

All digests tagged Claude Managed Agents docs

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

· 35:36

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

This workshop demonstrates building a sophisticated 'research desk' application using Claude Managed Agents (CMA). The system evolves from a simple console agent to a complex, multi-agent ecosystem capable of performing long-running, asynchronous tasks. Key architectural components include specialized skills (e.g., calling SEC EDGAR filings), subagent coordination, shared memory stores, and a self-supervision mechanism called 'Outcomes,' which uses a rubric and grader to ensure task completion and accuracy. The platform supports enterprise deployment through secure methods like Vaults and MCP tunnels.

Key takeaways

  1. Multi-Agent Orchestration and Skills 22:21

    Agents can be augmented with specialized skills (e.g., SEC EDGAR) and delegate tasks to specialized subagents. The main agent acts as an orchestrator, managing the workflow and coordinating multiple subagents to achieve a complex goal.

  2. Outcomes for Self-Supervision 29:01

    Outcomes define a task, a rubric, and a grader. This mechanism enables asynchronous, long-running tasks by having a subagent evaluate the main agent's work against the defined rubric, allowing Claude to automatically retry until the outcome is satisfied.

  3. Secure Credential Management (Vaults)

    For production use, credentials are managed via 'Vaults.' Instead of injecting real secrets, a placeholder is used, which is swapped out for the real value only at egress on specified host domains, enhancing security.

  4. Shared, Long-Running Memory 31:45

    The system supports long-running memory stores that can be shared across multiple sessions and agents, allowing the application to continuously learn and improve over time (a process referred to as 'dreaming').

Watch on YouTube Full article

Claude Managed Agents Q&A: Evals, CI/CD and Multi-Tenancy (Part 4 of 4) — Anthropic thumbnail

· 18:58

Claude Managed Agents Q&A: Evals, CI/CD and Multi-Tenancy (Part 4 of 4) — Anthropic

This workshop segment details advanced architectural patterns for deploying and managing Claude Managed Agents in enterprise environments. Key topics covered include integrating agent configurations into CI/CD pipelines using tools like `Ancho CLI`, achieving robust tenant isolation via workspaces, and implementing complex agent behaviors like the coordinator pattern for custom tools. The discussion emphasizes best practices for evaluation (Evals) and scaling compute resources using self-hosted sandboxes.

Key takeaways

  1. CI/CD for Agent Configurations

    Use `Ancho CLI` to wrap the API and manage agent resources (defined in YAML) in a Terraform-like manner. This allows durable, long-term resources to be version-controlled and updated via CI/CD pipelines. (0:00)

  2. Handling Custom Tool Waits

    When an agent is waiting for a custom tool result, external messages are blocked (resulting in a 400 error). To maintain continuous interaction, implement a coordinator pattern using a sub-agent to handle tool execution while the main agent remains free to receive messages. (16:30, 18:30)

  3. Data Quality for Evals 4:05

    The best practice for evaluation harnesses is to focus on gathering high-quality, well-defined data. While internal tooling can spin up thousands of parallel sessions for testing, the quality of the input data dictates the performance of the model. (2:45)

  4. Resource Isolation and Multi-Tenancy 14:08

    For true data segregation (e.g., legal requirements), agents should be deployed in individual workspaces or an organization per customer. Resources are bound to the workspace, and the platform recommends using a metadata field (like `customer ID`) to map sessions to specific customers within a single workspace. (8:48, 9:54)

  5. Scaling Compute Resources

    For custom resource allocations (e.g., higher memory or dedicated GPUs), utilize self-hosted sandboxes. This allows integration with external providers like Modal, which offers GPU capabilities, rather than relying solely on the platform's provided sandboxes. (12:10)

Watch on YouTube Full article