Schedules, reviews, and human control

Schedules

Schedules start supported workflows on a recurring rule. Users can create, edit, enable, pause, and delete schedule definitions.

RECURRING WORK

A schedule creates traceable workflow runs

1. 01

   Configure

   Choose workflow, cadence, timezone, and context.

2. 02

   Trigger

   Organ starts the next eligible occurrence.

3. 03

   Run

   The workflow keeps its own immutable input and state.

4. 04

   Review

   Inspect the resulting run, output, and errors.

A definition stores workflow type, venture, cadence, timezone, task/brief, workflow-specific configuration, and optional department, goal, resource, repository, or model context. Only Developer, Discovery, Research, Content, and Health Check appear as user-schedulable types. Department Head has its own orchestration path; Elaboration is a Discovery follow-on; Generic Task is one-off.

Review timezone and recurrence carefully. A paused schedule does not start new runs; it does not cancel work already running.

Scheduling semantics

• The configured timezone determines wall-clock interpretation; do not pre-convert the rule to server time.
• Pausing prevents future dispatches but leaves active workflow runs untouched.
• Editing a schedule affects future occurrences, not the immutable input already handed to a running workflow.
• A missed-run count signals that an occurrence could not dispatch; it does not automatically mean a duplicate should be started.
• Schedule deletion removes future intent. Resulting workflow records remain part of operational history.

Review points

Human control is expressed through workflow-specific actions:

• approve a discovery candidate;
• provide requested input to an escalation;
• approve a content draft;
• cancel an active run;
• retry eligible failed work;
• mark externally delivered content as published.

Decisions are recorded so later workflow steps can use them.

Failure handling

Retry only after correcting the underlying issue, such as an expired credential, unavailable model, invalid repository reference, or missing user input. Repeated blind retries can increase costs without changing the outcome.

What to expect

• Pending counts and escalation surfaces help locate work, while the final action can live on the workflow page that owns the decision.
• Schedule outcomes appear as resulting workflow runs. Use those runs to inspect execution history and errors.