Sunny Rekhi separates enterprise AI deployment into configuring an agent's behavior and building reusable product capabilities. Instructions, tone and human handoff rulesContext engineering designs how relevant instructions, evidence, state and tool information are assembled for a model's task. must fit each customer, while recurring requests should shape the shared platform.
Sunny Rekhi describes a shift from generalist agent engineers to specialized agent builders and software engineers as Decagon grows. The talk emphasizes agreeing on measurable outcomes early, assigning people with relevant industry experience and demonstrating value before expanding a deployment.
Sunny Rekhi argues that cheaper AI-assisted codingCode generation uses AI or another automated system to create source code from instructions, examples, schemas, or higher-level specifications. makes restraint more important: rapidly generated patches can create brittle systemsTechnical debt is the future work created by choices that make software harder to change or maintain.. Repeated integrations should become self-service features, and field teams should advise customers about prioritiesAI customer discovery investigates users, workflows and constraints to find problems where AI can create measurable value. rather than simply executing every request.
Watch on YouTube




