Contrary to the vision of free-wheeling autonomous agents, most business automation relies on strict Standard Operating Procedures (SOPs). Products like OpenAI's Agent Builder succeed by providing deterministic, node-based workflows that enforce business logic, which is more valuable than pure autonomy.

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.

Rather than programming AI agents with a company's formal policies, a more powerful approach is to let them observe thousands of actual 'decision traces.' This allows the AI to discover the organization's emergent, de facto rules—how work *actually* gets done—creating a more accurate and effective world model for automation.

Unlike tools like Zapier where users manually construct logic, advanced AI agent platforms allow users to simply state their goal in natural language. The agent then autonomously determines the steps, writes necessary code, and executes the task, abstracting away the workflow.

A critical error in AI integration is automating existing, often clunky, processes. Instead, companies should use AI as an opportunity to fundamentally rethink and redesign workflows from the ground up to achieve the desired outcome in a more efficient and customer-centric way.

The proliferation of SaaS tools forces thousands of employees to act as manual "human glue," moving data and connecting workflows between systems. The key value of AI agents is creating an intelligent layer to automate this mundane, connective work, freeing up employees for higher-value tasks.

Node-based workflow builders (like N8N or Zapier) require manual system design. The future is AI agents that, given access to tools and skills, can dynamically orchestrate the same complex workflows. The focus shifts from engineering a system to empowering a smart agent.

Don't put AI on a broken process. Before applying AI, first map and optimize your current workflows. AI can't fix fundamental flaws like too many approvals or unnecessary handoffs; it can only accelerate an already efficient process.

Simply adding AI "nodes" to a deterministic workflow builder is a limited view of AI's potential. This approach fails to capture the human judgment and edge cases that define complex processes. A better architecture empowers AI agents to run standard operating procedures from end to end.