How OpenAI turned its coding tools into dots, an always-on personal assistant
On this page
In late October 2026, OpenAI described how it evolved its coding tools into “dots”—always-on personal assistants that proactively observe, plan, and act across a developer’s workflow rather than responding to one-off prompts. The shift reflects a broader move from request-response coding agents toward persistent, ambient assistants that manage a stream of work.
Why It Matters
The “always-on” assistant marks a significant step in the agentic era: instead of being invoked for a single task, an AI coding assistant continuously monitors context, tracks open work, and interleaves its own actions with the user’s. This raises new questions about reliability, oversight, and how much autonomy a model should have over a long session.
This connects to the encyclopedia’s articles on agents and autonomy, agents tooling, and the generative agentic era. Persistent assistants also intensify the human–AI interaction questions covered in human–AI interaction.
Sources
Back to Recent News · Sub-article index.