Description
Task, Project, and Agent Workflows turn Dots' planning records into an executable terminal workflow for humans and coding agents. dots projects creates and updates project records; dots tasks handles creation, hierarchy, status changes, completion, deletion, and flips; dots agent provides the claim, progress, and completion protocol used by autonomous workers.
The workflow is designed for operators and coding agents. It uses the same authenticated, company-scoped service contracts as the rest of Dots, so terminal or protocol convenience never creates a second source of truth. Inputs are validated before or at the route boundary, and outputs preserve identifiers and structured details needed for a reliable next step.
Selling Points
- Keeps execution state in durable shared records instead of ephemeral terminal notes.
- Lets agents claim work explicitly, reducing duplicate effort across concurrent sessions.
- Preserves task hierarchy and project context while allowing focused command-line updates.
- Creates a consistent progress vocabulary that orchestrators can inspect and reconcile.
- Supports automation without bypassing the same task records humans review.
User Story
An orchestrator lists executable tasks under a project, an agent claims one, records a concise progress checkpoint, and completes it with the result attached to the shared workflow. Other sessions can immediately see that ownership and outcome. The result is a concrete, inspectable outcome that another person or automation can continue from without reconstructing hidden state.
Extension Surface
The feature is automatable: packages/cli/src/commands/tasks.ts, packages/cli/src/commands/projects.ts, and packages/cli/src/commands/agent.ts expose a fixed lifecycle over Tasks and Projects Dotabases. The rating reflects the most-open supported seam that is true for this capability, not a transitive implementation detail. The cited path is the operational proof: consumers can use the documented seam, while unsupported changes still require a core release.
Capabilities & Limits
- Capability: Project create, list, and update operations.
- Capability: Task creation, hierarchy reads, status updates, completion, deletion, and flips.
- Capability: Agent claim, progress logging, and completion commands.
- Limit: The commands execute the stored workflow; they do not decide product priority, resolve conflicting ownership, or replace the project's governing brief.
The limit is intentional product truth rather than missing documentation. Calls also remain subject to authentication, tenant selection, schema validation, and the permissions enforced by the authoritative service.
Implementation Map
packages/cli/src/commands/tasks.tspackages/cli/src/commands/projects.tspackages/cli/src/commands/agent.ts