Multi-Domain Support Conversations Dataset

This dataset combines 600 realistic customer support conversations from six different domains:

Customer Service (100 conversations)
E-commerce (100 conversations)
Financial Support (100 conversations)
HR / Onboarding (100 conversations)
Medical Helpdesk (100 conversations)
Technical Support (100 conversations)

Each dialogue is exactly 11 turns long and covers a wide variety of issues, making it ideal for training general-purpose AI assistants, chatbots, and customer support models.

Dataset Structure

Each conversation is stored as a JSON object with the following fields:

Field	Type	Description
`id`	integer	Unique identifier (1–600, grouped by domain)
`domain`	string	Original domain (e.g., `"customer service"`, `"e-commerce"`)
`problem`	string	Short description of the customer's issue
`customer_type`	string	Customer persona (see full list below)
`dialogue`	array	List of alternating customer/agent messages
`dialogue[].role`	string	`"customer"` or `"agent"`
`dialogue[].text`	string	The message content
`resolution`	string	One-sentence summary of how the issue was resolved

Customer Personas (with descriptions)

The dataset includes six distinct customer types, evenly distributed across each domain in a fixed cycle (conversations 1–6 contain one of each type, and the pattern repeats every 6 conversations up to 100):

frustrated user – Emotionally charged, expects fast resolution, may be abrupt.
confused beginner – Low technical literacy, needs step-by-step guidance, asks basic questions.
impatient executive – Busy professional, direct, demands efficiency and authoritative responses.
elderly user – Older, patient, requires clear explanations and warm treatment.
tech-savvy user – High technical knowledge, uses precise terminology, wants exact details.
calm and patient user – Collaborative, easy-going, follows instructions without friction.

This balanced distribution ensures your model learns to handle a wide range of communication styles and needs.

Example Conversation

Below is a sample conversation from the customer service domain (customer type: impatient executive):

{
  "id": 1,
  "domain": "customer service",
  "problem": "order never arrived",
  "customer_type": "impatient executive",
  "dialogue": [
    {
      "role": "customer",
      "text": "I placed an order 10 days ago and it still hasn't arrived. This is completely unacceptable."
    },
    {
      "role": "agent",
      "text": "I sincerely apologize for this delay. I'll look into this immediately. Could you provide your order number?"
    },
    {
      "role": "customer",
      "text": "Order number is #ORD-88421. I need this resolved today."
    },
    {
      "role": "agent",
      "text": "Thank you. I've pulled up your order. I can see it was delayed at the courier depot. I'm escalating this as high priority right now."
    },
    {
      "role": "customer",
      "text": "How long will an escalation actually take? I've heard that before."
    },
    {
      "role": "agent",
      "text": "I completely understand your frustration. I'm contacting the courier directly and will have a confirmed delivery window within 2 hours. I'll also apply a full shipping refund."
    },
    {
      "role": "customer",
      "text": "Alright. A 2-hour update is acceptable. What's the reference for this case?"
    },
    {
      "role": "agent",
      "text": "Your case reference is TKT-20394. I've also sent you an email confirmation with the courier's direct contact and your shipping refund confirmation."
    },
    {
      "role": "customer",
      "text": "I received the email. The refund is noted. I expect the delivery window shortly."
    },
    {
      "role": "agent",
      "text": "Absolutely. You'll receive an SMS from the courier within 90 minutes. Is there anything else I can assist with?"
    },
    {
      "role": "customer",
      "text": "No. Just make sure it's delivered. Thank you."
    }
  ],
  "resolution": "Order traced to courier depot delay. Case escalated with priority, shipping refund applied, and delivery window confirmed within 2 hours."
}

How to Use
Load with Python (local JSON)
python

import json

with open("multi_domain_support.json", "r", encoding="utf-8") as f:
    data = json.load(f)
    conversations = data["conversations"]

# Example: print all problem descriptions
for conv in conversations:
    print(conv["domain"], conv["problem"])

Load with Hugging Face Datasets
python

from datasets import load_dataset

dataset = load_dataset("ai-training-datasets/multi-domain-support", split="train")
print(dataset[0])

License

This dataset is released under the MIT License. You are free to use, modify, and distribute it for both research and commercial purposes.
Citation

If you use this dataset in your work, please cite it as:
text

@dataset{ai_training_datasets_2026,
  title     = {AI Training Datasets: Multi-Domain Support Conversations},
  author    = {AI Training Datasets},
  year      = {2026},
  version   = {1.0},
  publisher = {Hugging Face}
}

## 💼 Commercial licensing

This dataset is available for free under the MIT License for non-commercial use.  
If you need a commercial license, custom datasets, or the full version with all 600 conversations, contact me at:

📧 cybernovasg@gmail.com