IrisGo, a startup backed by Andrew Ng, looks to become the AI desktop buddy you never knew you needed | TechCrunch

Proactive AI systems aim to anticipate user needs and fulfill them before the user requests help. IrisGo is building a desktop companion that learns daily workflows and automates them with limited or no human prompting. The system records how a user completes tasks once and reuses the same process later without repeating instructions. A demo showed learning to place an online coffee order by capturing steps from selecting an item to entering payment details and purchasing. Iris includes a skills library with workflows such as email drafting, invoice processing, report building, and document summarization. It also adds learned tasks from desktop behavior to its action list. A coding assistant supports developers during their work.

"Industry insiders say the next big thing in AI is "proactive" systems: agents that can anticipate a user's needs - and fulfill them - before the user even knows what those needs are."

"The core idea is simple: show Iris how to do something once, and it remembers that process for future automated use - no repeat instructions needed."

"During a conversation with TechCrunch, Lai ran a demo, showing how Iris could learn to place a coffee order online. As I watched, Iris recorded the steps it took to select a latte from Philz Coffee (a popular Bay Area chain), fill out credit card information, and then hit purchase. Lai then asked Iris to repeat the order on its own; the agent dutifully complied."

"Iris comes with a built-in "skills" library - things like email drafting, invoice processing, report building, document summarization, and many other ready-to-use automated workflows. At the same time, Iris learns from the user's desktop behavior and automatically adds those tasks to its potential list of action items."

Read at TechCrunch