Mintlify co-founder Hahnbee Lee and Coinbase AI product lead Lincoln Murr discuss how software documentation changes when AI agents are readers. Hahnbee Lee emphasizes accuracy, context size and keeping documentation current.
Lincoln Murr describes Coinbase’s work to make services accessible to agents through APIsAn application programming interface is a defined way for software systems to request data or actions from one another., while acknowledging the need for security guardrailsA guardrail is a technical or procedural control that limits unsafe, disallowed, deceptive, or otherwise unwanted AI behavior. when agents access financial accounts. His discussion of stablecoins and agent paymentsAgentic commerce uses AI agents to assist with stages of buying and selling, such as product discovery, comparison and checkout. reflects Coinbase’s perspective.
Hahnbee Lee discusses automating parts of technical documentationWorkflow automation uses software or AI to complete a connected sequence of routine steps with less manual effort. while keeping human inputHuman-in-the-loop AI keeps a person involved in reviewing, correcting, approving, or guiding an AI system's work. for product insight and creative writing. Both speakers discuss the ongoing maintenance cost of building developer tools.
Watch on YouTube
