Question 1

AI turns that add no information the ERP already has

Accepted Answer

Customer address, service history, open tickets, installed equipment — all in the system of record. An AI copilot that interviews the technician about any of these is slower than the existing workflow. Prefill eliminates the friction.

Question 2

Free-text part numbers from the LLM

Accepted Answer

If a technician's natural language says "I need the 30-amp breaker" and the model emits a part number it made up, the order is wrong. Part numbers must come from the parts catalogue tool output, never from the model's own text. UI contract pattern.

Question 3

Workflow branching encoded in the system prompt

Accepted Answer

Service visits have well-known branches — warranty claim, paid service, callback. Encoding the branching logic in the prompt ("if X, then ask about Y") is fragile and expensive. A server-side state machine runs the branching; the LLM handles only the conversational ambiguity inside each branch.

Question 4

Customer-facing AI emitting text where the product needs structure

Accepted Answer

Appointment confirmations, quote summaries, and status updates in free text look acceptable in a demo and fall apart in production (wrong time zones, wrong units, inconsistent phrasing). Typed UI contracts let the model emit intent; the product renders the correct form.

Copilots de IA para plataformas de field service