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.
# Product: Wooden Study Table
## Dimensions
Width: 120 cm | Depth: 60 cm | Height: 75 cm
## Pricing
Standard finish: ₹8,999
Premium finish (walnut): ₹11,999
Custom size (add ₹2,000 to base price)
## Delivery
Delhi NCR: 3–5 business days (free)
Other cities: 7–10 business days (₹499 shipping)
Q: Can I get the table in a custom colour?
A: Yes — we offer custom RAL colour finishes for an additional ₹1,500. Contact us for samples.
Q: Do you offer EMI?
A: Yes — 0% EMI on all orders above ₹5,000 using HDFC or ICICI credit cards.
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:
## Discontinued products (do not quote these)
- Plastic Chair Model PC-100: discontinued as of March 2025, do not offer or quote
- Budget Desk Model BD-50: out of stock indefinitely, redirect to Model BD-60
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:
Do: Use simple, friendly language. Avoid jargon.
Do: Use short paragraphs — 2–3 sentences maximum per reply.
Do: Address the customer by their first name if you know it.
Don't: Offer any discount not listed in the knowledge base.
Don't: Confirm stock availability — say "subject to availability" instead.
Don't: Quote delivery dates — say "typically X days" instead.
Do: If the customer asks for a bulk order above 20 units, collect their name and requirement and say our sales team will call them.
Do: Escalate to a human if the customer expresses frustration or uses the word "complaint".
Escalation logic
AI staff escalates to human when:
- The customer explicitly asks for a human
- The AI’s confidence is below the threshold (usually after 2–3 failed answer attempts)
- 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:
- Check the Inbox for recent escalated conversations
- Read what question triggered the escalation
- Add a direct answer for that question to the knowledge base
- 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:
Don't: If you're not certain of a price from the knowledge base, say "Let me get that confirmed for you" and escalate to a human.
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.
