For core business automations, agentic AIs that "guess" are expensive and unreliable. A superior approach uses tools that convert natural language into deterministic, code-like workflows, which run consistently and use AI only when necessary.

Jan Oberhauser argues that AI is not a universal solution for every problem. For business-critical processes, companies should combine AI with deterministic logic because deterministic code is cheaper, faster, and 100% reliable. Integrating AI steps with rule-based routing and human approval checkpoints prevents erratic failure modes in production and delivers measurable ROI rather than costly, uncontrolled experimentation.

To control spiraling AI costs, teams should first determine if a task can be solved with deterministic, rules-based logic. Using AI for problems that have a straightforward, non-AI solution is an inefficient use of resources and introduces unnecessary variability and expense.

Wade Foster argues that for most business automation, delegating tasks to an AI agent is inefficient. Instead, an AI should be used to *build* a deterministic workflow (i.e., traditional code) which is cheaper and more reliable for execution. AI's reasoning is best reserved only for parts that truly require it.

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.

Using a powerful generative AI model for simple, repeatable queries like "What's my order status?" is inefficient and costly. These are better suited for cheaper, deterministic AI or standard NLU, reserving expensive frontier models for complex, multi-threaded conversations where they add real value.

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.

Pega's CTO advises using the powerful reasoning of LLMs to design processes and marketing offers. However, at runtime, switch to faster, cheaper, and more consistent predictive models. This avoids the unpredictability, cost, and risk of calling expensive LLMs for every live customer interaction.

The most powerful automations are not complex agents but simple, predictable workflows that save time reliably. The goal is determinism; AI introduces a "black box" of uncertainty. Therefore, the highest ROI comes from extremely linear processes where "boring is beautiful" and predictability is guaranteed.