To maximize leverage, reframe every SDLC component—docs, tests, review agents—as a way to 'prompt inject' non-functional requirements into the agent. This approach teases out expert knowledge from engineers' heads and makes it part of the automated system, guided by the agent's mistakes.

As companies deploy numerous task-specific AI agents (e.g., payroll, payments), the user experience risks fragmentation. Xero's solution is a 'super agent' that manages all sub-agents, orchestrating actions, transferring information, and applying user preferences globally to create a cohesive system.

Even without technical skills, you can develop custom applications by treating your AI coding agent as a dedicated developer. Frame the project with a strong sense of mission and purpose. Persistently push back when the agent says something is impossible. This approach transforms the interaction from a simple command-and-response to a collaborative, goal-oriented development process.

A static agent doesn't improve. To create a continuously learning system, build a secondary agent that observes a human's corrections. This "learner" agent synthesizes patterns from the feedback and suggests updates to the primary agent's instructions, creating a powerful self-improvement cycle.

Getting high-quality results from AI doesn't come from a single complex command. The key is "harness engineering"—designing structured interaction patterns between specialized agents, such as creating a workflow where an engineer agent hands off work to a separate QA agent for verification.

Agents quickly become outdated. To manage this lifecycle, build specific 'upgrade skills' that facilitate migration to new models. For larger-scale management, deploy 'meta-agents' whose sole job is to monitor other agents, identify outdated ones, and trigger the upgrade process.

Instead of relying on traditional tutorials, non-technical individuals can successfully build complex AI agent teams by using a conversational AI as an interactive, patient, step-by-step coach. This approach democratizes access to advanced technology, bypassing conventional learning methods.

A primary AI agent interacts with the customer. A secondary agent should then analyze the conversation transcripts to find patterns and uncover the true intent behind customer questions. This feedback loop provides deep insights that can be used to refine sales scripts, marketing messages, and the primary agent's programming.

The best agentic UX isn't a generic chat overlay. Instead, identify where users struggle with complex inputs like formulas or code. Replace these friction points with a native, natural language interface that directly integrates the AI into the core product workflow, making it feel seamless and powerful.