You have run a Task from start to finish. What you read next depends on what you are trying to achieve.
I want to understand how this actually works.
Begin with How a Task becomes a pull request, then Agent roles. Together they outline every stage and who carries it out.
After that, Specifications is the most valuable page in the documentation — the quality of what Coroid builds depends on the quality of what it is asked to build.
I want to run more work at once.
Read Capacity and agent slots. Slots are the unit of parallelism, and the most common source of confusion is expecting them to make a single Task run faster. They do not.
Then Tasks, plans, sprints and lanes to learn how to structure work larger than one pull request.
I want better output.
There are three levers, ordered by impact:
- Write better Specifications. See Specifications.
- Give Coroid more context. See Project context.
- Change the models. See AI profiles. A profile contains a model for every agent, so moving a piece of work up a profile improves planning, building and review together.
I want tighter control over what ships.
Quality gates explains how policy determines what can pass, and where a gate can halt a Task.
I want to connect my other tools.
The Integrations overview shows what connects to what and in which direction — issue trackers in, chat both ways, review evidence onto pull requests.
I want to know what something means.
Glossary defines every term the interface uses, and Task statuses explains every status a Task can have and what to do about it.