Categories › AI & Agents › Multi-agent, orchestration & workflows
INVOKE THIS SKILL when building, testing, or deploying Managed Deep Agents in LangSmith. Walks a user through their first agent end to end — interviewing them about what they want to build, mapping it onto what MDA can actually do, then scaffolding and deploying it with the mda CLI. Routes to the official docs page for each capability: instructions, skills, tools, MCP, connections, middleware, sandboxes, browser use, memory, identity, subagents, schedules, channels, runtime, Context Hub, deploy,
Not tested by KitScout yet. When our harness runs it, pros, cons and the tasks we tried appear here, with the date and evidence.