Work reaches Coroid via several routes, all leading to the same execution path — specification, plan, build, verify, review, pull request.
| Route | Use when |
|---|---|
| New Work | Someone has a requirement and is here to describe it. |
| Import issues | The request already exists in Jira, Linear, Trello or GitHub Issues. |
| Ask Coroid | You prefer to describe it verbally. |
| Schedules | The trigger is time. |
| Sentinel | The trigger is a condition becoming true. |
| Hooks | The trigger is a platform event. |
You choose the outcome.
No matter how the work arrives, you decide what it will become. The New Work form asks for this first, and the rest of the form adjusts based on your answer:
| Routing | Produces |
|---|---|
| One executable task | A single task, resulting in one pull request. |
| Phased work plan | A phased plan you approve before any code is written. |
| Report | A generated report. |
| Schedule | A recurring monitor. |
Task or plan?
The useful test is reviewability. If the finished work is one pull request a colleague could read in one sitting, it is a task. If it requires several sequential changes, or you want to approve the approach before any of it is built, it is a plan.
When in doubt, opt for a plan for anything substantial. A plan provides an approval checkpoint before code exists, which is the cheapest time to change your mind. A task that proves too large simply runs out of space.
Imported work
Issues imported from a tracker do not start executing automatically — you still need to route them. A backlog is a wish list, and not everything on it should be handled by an agent without someone making a decision. See Importing work.
Automated entry
Schedules, Sentinel and hooks start work without human intervention, differing only in their trigger: time, an observed condition, and a platform event.
All three use real agent slots and real model resources. Assign automated work a lower priority than work someone is waiting on — see Capacity and agent slots.