Choose a work mode

Start with the behavior the work needs, not the label. All four modes can use project context and agent capabilities; they differ mainly in who initiates the work, how continuity is kept, and what people return to afterward. Workspace connectors are available in their projects by default, and you can turn off an inherited connector for the particular project, chat, or agent that should not use it. Conversationally created agents use only their draft-reviewed connections and do not inherit future workspace credentials; see Create your first agent.

Need	Choose	History
A person steers the next step	Chat	One continuing conversation
A persistent role should notice and act	Agent	One ongoing conversation for messages, wakeups, and channels
A defined job should run at a known time	Automation	A separate history for every run
People should return to a maintained artifact	Dashboard	Build and refresh history with saved versions

Use a chat for exploration

Choose a chat when a person should stay in the loop, the goal is still changing, or each next step depends on the last answer. Chats are also the best place to prototype instructions before turning them into repeatable work.

Use an agent for responsibility

Choose an agent when the work has an ongoing owner, a persistent conversation, and standing instructions that should survive beyond one run. An agent can receive direct messages, be woken manually, maintain one-time and recurring wakeups, and participate through connected channels.

If you are not sure which agent to staff first, start with one responsibility you want to hand over. Open Agents → New agent to choose a creation path, then give the coworker that responsibility.

Do not choose an agent only to obtain a schedule. If every occurrence should start from a stable job definition with independent history, an automation is simpler.

Use an automation for a defined trigger

Choose an automation when the prompt and trigger are known in advance and each run can be evaluated as a repeatable job. Automations support manual-only, one-time, and recurring schedules. If scheduled runs are missed, d5s does not run them all later to catch up.

Use a dashboard for a maintained output

Choose a dashboard when people should return to a maintained output and its sources. Dashboards can use widget boards or apps, and the build chat stays available for changes. If the dashboard shows Draft, editors review app changes before they replace the current view. Widget boards keep their board workflow. See Dashboards for publication, source refresh, and saved history.

You can begin interactively and promote the stable pattern later. The important boundary is whether the work needs dialogue, durable responsibility, a trigger, or a maintained output.