The most valuable AI agents don't wait for user queries. The real breakthrough comes when agents shift from a reactive, pull-based model to a proactive, push-based one, like automatically delivering a daily summary. This eliminates user friction and makes the agent feel indispensable.

While CLIs were an important stepping stone for agentic AI, the industry is rapidly moving back to rich Graphical User Interfaces (GUIs). These new UIs are designed for simultaneous collaboration between a human user and an AI agent, offering a more powerful and intuitive experience.

Because AI agents operate autonomously, developers can now code collaboratively while on calls. They can brainstorm, kick off a feature build, and have it ready for production by the end of the meeting, transforming coding from a solo, heads-down activity to a social one.

The speed of models like SWE 1.7 is more than a convenience; it fundamentally changes user behavior. It eliminates the awkward latency gap where tasks are too slow for real-time interaction but too fast to fully context-switch. This enables a new "watch it work" workflow, keeping users in a state of flow.

The most advanced use of AI agents involves breaking the 'prompt-wait-review' cycle. Features like Codex's 'steer' and side panel allow users to inspect, annotate, and redirect the AI while it's working. This shifts the paradigm from sequential turns to a continuous, parallel collaboration.

Most AI tools are single-player experiences. Linear is designing its agent sessions to be shared, collaborative spaces. Multiple people, like a PM and a designer, can jump into the same chat with an agent, see its work, and give it feedback together, collapsing the collaboration loop.

Unlike web apps where users expect instant responses, messaging apps have a built-in expectation of delay. This makes them the ideal interface for AI agents that need time to perform ambitious, complex tasks without frustrating the user.

Sam Altman highlights a key feature in new coding models: the ability for a user to interrupt and steer the AI while it's in the middle of a multi-hour task. This shifts the workflow from one-shot prompting to dynamic management, making the AI feel more like a true coworker you can course-correct in real time.

Long-horizon agents, which can run for hours or days, require a dual-mode UI. Users need an asynchronous way to manage multiple running agents (like a Jira board or inbox). However, they also need to seamlessly switch to a synchronous chat interface to provide real-time feedback or corrections when an agent pauses or finishes.