Cues' initial product was a specialized AI design agent. However, they observed that users were more frequently uploading files to use it as a knowledge base. Recognizing this emergent behavior, they pivoted to a more horizontal product, which was key to their rapid growth and product-market fit.

Before launch, product leaders must ask if their AI offering is a true product or just a feature. Slapping an AI label on a tool that automates a minor part of a larger workflow is a gimmick. It will fail unless it solves a core, high-friction problem for the customer in its entirety.

Initially a mobile-first video editor, CapCut's rising usage on desktops by social media managers was a crucial market signal. It showed that professional workflows requiring collaboration and approvals are ill-suited for mobile, revealing an underserved B2B segment for web-first platforms.

A key reason Figma won was its cloud-based, real-time collaboration. The trend of using local AI dev tools (like Cursor) is a step backward in this regard, reintroducing friction around sharing work and getting feedback, the very problems that led designers away from local files in the first place.

The founder's startup idea originated from a side feature in another project: a "SQL janitor" AI that needed human approval before dropping tables. This single safety feature, which allowed an agent to request help via Slack, was so compelling it became the core of a new, revenue-generating company within weeks.

Scribe started by building workflow automation, viewing documentation as a simple byproduct. Customers, however, found the automation only incrementally valuable but saw the documentation as a game-changing solution. Listening to this strong user pull led to the company's successful pivot.

The IDE Zed was built for synchronous, Figma-like human collaboration to overcome asynchronous Git workflows. This foundation of real-time, in-code presence serendipitously created the perfect environment for integrating AI agents, which function as just another collaborator in the same shared space.

For complex features, a 17-page requirements document is inefficient for alignment. An interactive AI-generated prototype allows stakeholders to see and use the product, making it a more effective source of truth for gathering feedback and defining requirements than static documentation.

Initially building a tool for ML teams, they discovered the true pain point was creating AI-powered workflows for business users. This insight came from observing how first customers struggled with the infrastructure *around* their tool, not the tool itself.