Sendoso's initial strategy of giving every employee AI tools resulted in chaos: duplicate agents, inconsistent quality, and permission issues. They reversed course, centralizing development into an "Agentic Pod" model to maintain control, quality, and strategic focus.

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.

To build a useful multi-agent AI system, model the agents after your existing human team. Create specialized agents for distinct roles like 'approvals,' 'document drafting,' or 'administration' to replicate and automate a proven workflow, rather than designing a monolithic, abstract AI.

When each employee has a personal AI agent, the agents naturally adopt the specializations of their human counterparts. The head of growth's agent becomes the go-to expert on growth metrics, creating a parallel organization of specialized bots that mirrors the human org chart.

Every initially gave each employee a personal AI agent but found this created a massive maintenance burden and knowledge silos. They shifted to shared agents focused on team functions (e.g., analytics). This centralizes maintenance, improves continuity when employees leave, and scales benefits across the entire team.

Moving past chaotic "hackathons," effective AI implementation needs a designated leader who knows the team's processes inside and out. This person shepherds the strategy, ensuring agents are built on a solid foundation and integrated smoothly, preventing a proliferation of uncontrolled, low-quality bots.

To control costs, security, and governance, enterprises are moving from interactive, ad-hoc agent use to a 'software factory' model. This approach systematizes the entire work lifecycle, automating processes and minimizing the risks associated with inconsistent human operation of powerful AI tools.

Making automation too easy can lead to "slop"—numerous duplicate and poorly managed workflows. Serval solves this with an AI agent that understands existing automations, preventing redundancy and suggesting consolidation or modification instead of creating new, duplicative workflows.

Instead of a monolithic AI, create a team of agents with specific roles (e.g., 'Debbie the assistant,' 'Soren the engineer'). This human-like model makes it easier to manage capabilities, control access, and conceptualize the system's functions because it maps to our innate understanding of human teams.