By living on iMessage, Lindy automatically gains access to Siri, CarPlay, and iOS Shortcuts. This strategic choice allows users to interact with the assistant via voice or car commands without Lindy needing to build and maintain those features itself, piggybacking on Apple's platform.

In a hybrid model, an AI can handle a customer conversation but escalate ambiguous micro-tasks, like interpreting a photo for a warranty claim, to a human agent via a private message. The human provides a quick verdict, allowing the AI to continue the interaction seamlessly without the customer knowing.

Contrary to the trend of building elaborate dashboards to track AI agents, a simpler approach is more effective. The guest manages his agent, Larry, through simple text messages on WhatsApp, treating him like a human employee. This avoids over-engineering and keeps the interaction natural and efficient.

Current communication tools like Slack are ill-suited for managing AI agents. The future lies in integrated "super apps" that combine chat interfaces with built-in credential management, file systems, and API key provisioning, creating a unified environment for human-agent 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.

Instead of setup menus, users onboard Lindy through conversation, just as they would with a human. Telling it "after my meetings, I want you to update my CRM" is the entire configuration process, drastically lowering the adoption barrier for non-technical users.

To make an AI assistant feel more conversational, architect it to delegate long-running tasks to sub-agents. This keeps the primary run loop free for user interaction, creating the experience of an always-available partner rather than a tool that periodically becomes unresponsive.

Instead of helping users draft messages, the true evolution of communication is AI agents negotiating tasks like scheduling meetings directly with other agents. This bypasses the need for manual back-and-forth in apps like iMessage.

The most powerful current use case for enterprise AI involves the system acting as an intelligent assistant. It synthesizes complex information and suggests actions, but a human remains in the loop to validate the final plan and carry out the action, combining AI speed with human judgment.