Moving beyond simple trigger-based automations, the real power of AI workforces lies in proactive execution of undefined workflows. This requires giving agents clear goals, tools, and permission to use probabilistic reasoning to identify and act on new opportunities, which removes the human as the primary bottleneck.

To get high-quality, autonomous work from an AI agent, you must treat it like a new hire, not just give it a simple prompt. You must provide a clear goal, specific skills (pre-defined knowledge), the right tools (APIs, etc.), and rich context (company data).

The biggest gains from AI come not from automating steps in an existing process, but from starting with the desired outcome and co-creating a new workflow with AI. This "first principles" approach leverages AI's capabilities far more effectively than piecemeal automation.

When mapping a process to apply AI, don't just document current workflows. Instead, design the ideal process you would have with zero constraints (e.g., unlimited time, budget). This approach allows you to leverage AI to automate ideal-state tasks, like research or content repurposing, that are currently impossible due to resource limitations.

A major pitfall in designing agent systems is simply automating existing human workflows. These processes are built around human limitations like attention span. Effective agentic design requires rethinking work from first principles to leverage the unique, non-human capabilities of AI.

Don't assume AI can effectively perform a task that doesn't already have a well-defined standard operating procedure (SOP). The best use of AI is to infuse efficiency into individual steps of an existing, successful manual process, rather than expecting it to complete the entire process on its own.

The most significant gains from AI will not come from automating existing human tasks. Instead, value is unlocked by allowing AI agents to develop entirely new, non-human processes to achieve goals. This requires a shift from process mapping to goal-oriented process invention.

Don't view AI tools as just software; treat them like junior team members. Apply management principles: 'hire' the right model for the job (People), define how it should work through structured prompts (Process), and give it a clear, narrow goal (Purpose). This mental model maximizes their effectiveness.

Building AI systems around rigid "workflows" is a mistake because knowledge work lacks predictable "happy paths." A superior mental model is "delegation," where the AI is treated like a human assistant. You delegate a task area, and the AI is expected to learn and adapt to novel circumstances, not just execute a process.