What "agents" means in RG AI today - and what it doesn't mean.
Note: This is one of the most commonly misunderstood parts of the product, so it's worth being precise: RG AI does not run separate autonomous background agents today.
It's a single conversation with your chosen model, not independent agents working in parallel. When you ask RG AI to plan something, write code, research a topic, draft something, or debug an error, you're getting one model doing one of five kinds of work well within that same chat.
True multi-step autonomous agents (the model taking actions across multiple turns without you driving each step) are on the roadmap but not built.
Note: This is planned, not live yet. It's shown here so the roadmap is transparent - nothing on this page describes a feature you can use today.