AI Workflows & Teams
Organize processes, materials and responsibilities so work can be repeated and shared.
Make a one-off method repeatable and transferable
Recommended reading
Should AI Work Live in a Project, Folder, or Conversation?
Give projects, files and conversations distinct roles, with an established place for important results.
All articles
- Agents & CollaborationHow Claude Distinguishes Prompts, Skills, Tools, and SubagentsClaude's public guidance distinguishes a one-time prompt, a reusable skill, tool or MCP access, and a scoped subagent by the job each layer performs.
- Agents & CollaborationWhen Does Claude’s Multi-Agent Guidance Recommend Splitting Work?Claude's public multi-agent guidance points to context overload, true parallelism, and independent verification—not a default need for more agents.
- Agents & CollaborationWhat Claude’s Public Engineering Guides Teach About Reliable AgentsA practical guide to Claude and Anthropic's public material on harnesses, multi-agent systems, skills, evaluation, and human control in reliable AI workflows.
- Knowledge & MemoryAI Output Is Not Knowledge: Add a Candidate Layer and Human ReviewDo not write every AI output into a knowledge base. Use a candidate layer that preserves sources, scope, uncertainty, sensitivity, and human review.
- Agents & CollaborationAvoid Agent Sprawl: When to Use a Task, Board, Skill, or ProfileDo not turn every request into an agent. Use five questions to choose a Task, Board, workspace, Skill, or Profile and understand each boundary.
- Agents & CollaborationSeparate Personal and Work AI Systems with Minimal Information HandoffsDesign separate personal and work AI entry points, share only the constraint that work needs, and do not mistake Profiles for security isolation.
- Agents & CollaborationFrom Dispatcher to Work Chief of Staff in a Multi-Agent SystemBefore routing ambiguous work, clarify the outcome, identify unknowns, choose the smallest structure, and define an explicit handoff.