Drake Surach introduces the interface and explains a goal, context, action and output framework for promptsPrompt engineering is the practice of designing and refining instructions, context, examples, and constraints to obtain useful AI outputs.. A business-content example contrasts generic questions with requests grounded in an audience, constraints and a desired deliverable. Follow-up questions refine the result instead of treating the first response as final.
The tutorial demonstrates web search, deeper research, file analysis and image understanding and creation. It then builds reusable personal instructions through an interview and organizes project-specific files and rulesContext engineering designs how relevant instructions, evidence, state and tool information are assembled for a model's task.. These demonstrations emphasize context and source inspection, although generated citations or an image-based diagnosis are not guarantees of correctness.
Drake Surach connects a calendar and distinguishes reading information from actions that change itAn agent permission boundary defines and enforces which resources and actions an automated agent is allowed to use., including configurable permissions. He packages a news briefing as a reusable skillAn AI agent skill is a reusable package of instructions, resources, and tool guidance for performing a bounded kind of work., schedules a daily briefingWorkflow automation uses software or AI to complete a connected sequence of routine steps with less manual effort. and generates an interactive automation calculator. The closing section contrasts conversational work with task-oriented creation. Interface, pricing and account-access claims are presented as the creator's demonstration at recording time, not universal product guarantees; training promotions are omitted.
Watch on YouTube




