The stack if you want to know

STL Automate's internal production automation runs on self-hosted n8n, an open-source workflow automation platform that handles triggers, logic branching, API calls, and integrations.

We chose n8n because it gives us fine-grained control over every node in the workflow without abstracting away the logic. When something goes wrong, we can see exactly where and why, not just that something failed.

Client deployments may be customer-owned or STL-managed depending on scope. Credentials and workflows are separated according to the approved deployment architecture.

The Phone Receptionist uses programmable voice infrastructure selected for the needs of each deployment. Provider, conversation model, speech services, and routing are configured for the approved call flow.

Where supported, call events and metadata can route into n8n for approved classification, logging, notifications, and follow-up preparation.

Provider, model, and phone-routing choices are tested and validated for each implementation before production use.

Scoring and routing begin with explicit business rules. Where useful, AI-assisted classification can help interpret unstructured inputs such as email bodies and call transcripts.

Criteria, thresholds, models, labels, and routing rules are defined per implementation. They are tested against the customer's actual use cases before they affect production behavior.

Knowledge sources are selected according to the workflow. Customer-approved systems remain authoritative where applicable, and generated drafts can be grounded in the business information approved for that use.