LLM integration patterns for business applications

Practical AI starts with the boundary

The first decision is not which model — it's where the LLM sits relative to your system of record. We treat the model as an untrusted advisor: it proposes, your domain logic disposes.

Self-hosted or API?

| Need | Choose | |------|--------| | Strict data residency | Self-hosted (Ollama, llama.cpp) | | Frontier reasoning, low volume | API (OpenAI, Groq) | | Predictable cost at scale | Self-hosted with a gateway |

Always go through a gateway

Every model call should pass through one internal gateway that owns timeouts, retries, a token ceiling, and a cost kill-switch. Calling the SDK directly from twelve places is how you get a surprise invoice.

Human-in-the-loop by default

For anything that writes to the system of record — extracted invoice data, a proposed schedule — surface low-confidence outputs for review. The LLM removes the typing, not the accountability.