Training Dataset for NLU-Powered Customer Service Chatbot
Generates a structured dataset of intents, entities, and dialogues to train a customer service chatbot in Brazilian Portuguese.
Create a complete, high-quality dataset for training or refining a customer service chatbot, covering primary customer intents with natural language variations.
At a glance
Access
Free prompt
Open to copy — no account or payment needed.
Prompt objective
Create a complete, high-quality dataset for training or refining a customer service chatbot, covering primary customer intents with natural language variations.
Real use case
FarmaVida, an online pharmacy network processing 20,000 orders per month, wants to implement a WhatsApp Business API chatbot via Zendesk to automate 50% of inquiries. They need Brazilian Portuguese training data with colloquial language variations.
Customize these fields first
Replace the placeholders with your own context before you run the prompt. That usually improves the first output more than adding more instructions later.
Prompt
Generate a complete training dataset for the customer service chatbot at [COMPANY NAME], operating in the [INDUSTRY] sector, for deployment on [PLATFORM: WhatsApp Business API/Webchat/Instagram DM]. **Structure by Intent (minimum 15 intents):** For each intent, provide: - Intent name (slug): e.g., `check_order_status` - Functional description - 20 variations of how customers might express this intent (including: - Formal language:
Open directly in an AI — the text is pre-filled:
How to use this prompt
- 1Replace the key placeholders first: COMPANY NAME, INDUSTRY, PLATFORM: WhatsApp Business API/Webchat/Instagram DM.
- 2Replace any bracketed placeholders like [this] with your own context.
- 3Add extra background information when you want more tailored results.
- 4Combine multiple prompts in one conversation when you need a richer output.
- 5Save your best-performing prompts so they are easy to reuse later.
Next best step
Open the guide first, then branch only if you still need more.
A guide for sales teams that want better prospecting, follow-up, qualification, and pipeline support with AI.
If this prompt is close but not quite right, generate variants next. If the job is recurring, move into the course library after the guide.
Related prompts
View allKnowledge Base Structure for Self-Service Customer Support
Creates a complete, navigable knowledge base that allows customers to find answers without contacting a support agent.
Best for
Reduce repetitive ticket volume by at least 30% through a well-structured knowledge base with clear articles and intuitive navigation.
Interactive Decision Tree Self-Service Portal
Design a self-service portal with guided flows that lead customers to the right answer through sequential questions.
Best for
Create a self-service experience that goes beyond static FAQs, guiding customers through resolution via a visual and interactive decision tree.
Existing FAQ Optimization with Search Analysis and Content Gap Assessment
Audit and optimize an existing knowledge base using search data, recurring tickets, and gap analysis.
Best for
Transform an underutilized FAQ into an efficient self-service resource by identifying missing content, outdated articles, and improvement opportunities.
Short-Video FAQ for TikTok, Reels, and YouTube Shorts
Short video scripts answering the most frequently asked customer questions in a native social media format.
Best for
Create a series of 30-60 second FAQ videos that function as social media content AND as a support resource, reducing tickets and increasing engagement.
Explore other prompt categories
Move sideways into adjacent libraries when the current category is not the full answer.
Every prompt here is free. The course teaches the thinking behind them.
Copy as many prompts as you like. When you want to move from single prompts to a repeatable AI workflow, Learn AI in 30 Days walks through it, one day at a time.
Buy the course once ($15/$20 by length), or go all-access for $10/mo with a verifiable certificate.