The web will not be "API-fied" for AI agents; instead, computer use models that leverage vision will become the primary drivers of web interaction. Because the vast majority of the web is built for human consumption—often relying on complex, non-standardized rendering rather than clean data endpoints—expecting a transition to universal APIs is unrealistic. Current web infrastructure is too fragmented and slow-changing to accommodate such a shift. Consequently, AI agents must function like human users, navigating through pixels, clicking buttons, and executing code to extract information. As these models improve in accuracy, latency, and cost-efficiency, they will effectively create a new layer of automation on top of existing web messiness, ultimately providing the functional equivalent of an API without requiring websites to fundamentally restructure their underlying architecture.
Sign in to continue reading, translating and more.
Open full episode in Podwise
