Skip to main content
This guide covers advanced configuration techniques for consultants who want to squeeze the best performance out of StoreTalk’s AI staff.

​
Knowledge base structure for accuracy

The single biggest factor in AI response quality is knowledge base structure. Here are the patterns that work best:

​
Hierarchical headings

Use # and ## headings to group content. The AI uses headings as context anchors — it knows that “Price: ₹499” refers to the product listed in the heading above it.

​
Q&A format for FAQs

Write FAQs exactly as customers ask them. The AI matches customer questions against the question text in your KB.

​
Explicit negative rules

If there are things the AI should never say (e.g. a discontinued product, a price you’re renegotiating), add explicit exclusion notes:

​
Persona tuning via Dos & Don’ts

The Dos & Don’ts field is the most powerful lever for shaping AI personality and behaviour. Use it to: Set the communication style:
Set hard business rules:
Set escalation triggers:

​
Escalation logic

AI staff escalates to human when:
  1. The customer explicitly asks for a human
  2. The AI’s confidence is below the threshold (usually after 2–3 failed answer attempts)
  3. A custom escalation rule in Dos & Don’ts is triggered

​
Reducing false escalations

If the AI escalates too often, the knowledge base content is likely too thin or too vague. Before adjusting escalation settings, first:
  1. Check the Inbox for recent escalated conversations
  2. Read what question triggered the escalation
  3. Add a direct answer for that question to the knowledge base
  4. Re-test

​
Reducing missed escalations

If the AI is confidently answering questions it shouldn’t (e.g. confirming prices that aren’t in the KB), add explicit Don’ts:

​
Multi-staff routing

When a client has multiple AI staff members, StoreTalk’s orchestrator (StoreAgent) routes each incoming message to the most relevant specialist. To make routing work well:
  • Give each staff member a distinct, narrow scope — a Sales Executive should not also know return policies
  • Use clear, specific knowledge base files — one file per topic, not one large file for everything
  • Set the staff member’s language explicitly — if you have a Hindi-only staff member for regional customers, set it to Hindi
Always run at least 20 test messages after a new setup before handing over to the client. Cover edge cases: questions the AI shouldn’t answer, requests for discounts, complaints, and multi-part questions.