Build a Voice Receptionist for Your Business · 25 min · Vapi

Knowledge Base — Business FAQ

A system prompt bloated with every FAQ answer you own is slower, less focused, and paradoxically worse at answering the one question a caller actually asked.

Hiring signal: Structuring business knowledge for a voice agent specifically -- short, structured, latency-aware -- is a real and underrated skill distinct from general RAG or prompt-stuffing patterns.

What you will learn

Create a structured business config (services, pricing, hours, FAQ)
Inject it into the system prompt without bloating it
Test against 10 realistic caller questions and tune for naturalness

What You're Building

A structured business config — services, pricing, hours, common questions and answers — injected into the assistant so it can answer real business questions, without turning the system prompt into a wall of text the model (and the latency budget) has to wade through on every single turn.

Structured, not stuffed

{
  "businessName": "Apex Consulting",
  "hours": "Monday-Friday, 9am-5pm Eastern",
  "services": [
    { "name": "Strategy Consultation", "price": "$150/hour" },
    { "name": "Full Engagement", "price": "Custom quote after initial consultation" }
  ],
  "faq": [
    { "q": "Do you offer free consultations?", "a": "We offer a free 15-minute intro call to see if we're a good fit." },
    { "q": "Where are you located?", "a": "We're fully remote, working with clients nationwide." }
  ]
}

Structured data like this, injected as a clearly delimited block in the system prompt ("BUSINESS INFO: ..."), is easier for the model to reference precisely than the same information written as flowing prose -- and easier for YOU to update later (change a price in one JSON field, not hunt through paragraphs of prompt text).

Short prompts matter more in voice than in text -- this isn't the same tradeoff as a text chatbot
A text-based RAG chatbot can afford a fairly long system prompt with lots of context, because there's no live human waiting through the processing time. A voice agent's system prompt gets re-processed (at least in part) on every turn of a live phone call -- a bloated prompt with 40 FAQ entries the caller will never ask about is real, avoidable latency, not just messier prompt engineering.

Unlock the full lesson

You've read the first 2 sections. The rest of this lesson covers Test against real questions, tune for how they're actually asked, What you're building today — plus a hands-on lab, quiz, and project artifact.

Create a free account to unlock Phase 0 and Phase 1 of every course — no credit card.

Key terms in this lesson

System Prompt