​
Welcome to Vambe Kategor

Hello there! Welcome to the world of Vambe Kategor, your new favorite tool for analyzing conversations, extracting insights, and auditing interactions. Whether you’re diving into customer service analytics, training chatbots, or managing complex conversations, we’ve got you covered. Let’s walk through how to get started and make the most of this powerful API.

​
Your Journey Begins: Setting Up

​
Step 1: Create Your Organization

First things first, let’s get you set up with an organization. Think of this as your home base in the Vambe Kategor system.

Here’s how to do it:

curl --request POST \
  --url https://kategory-api-production.up.railway.app/api/organizations \
  --header 'Content-Type: application/json' \
  --data '{
  "name": "Your Awesome Company",
  "nickname": "AwesomeCo"
}'

Once you run this command, you’ll receive an access token. Keep this token safe – it’s your key to the kingdom and you’ll need it for all future requests.

​
Step 2: Analyze Your First Conversation

Now that you’re set up, let’s dive into the heart of what Vambe Kategor does best – analyzing conversations. This is where the magic happens!

Here’s how to submit a conversation for analysis:

curl --request POST \
  --url https://kategory-api-production.up.railway.app/api/analyze \
  --header 'Content-Type: application/json' \
  --header 'x-api-key: YOUR_ACCESS_TOKEN_HERE' \
  --data '{
  "user_id": "user123",
  "conversation_id": "convo456",
  "conversation": [
    {
      "role": "user",
      "content": "Hello, I need help with my order",
      "agent_id": "agent789",
      "message_id": "msg001"
    }
    // Add more messages here
  ],
  "agents": [
    {
      "agent_id": "agent789",
      "prompts": [
        {
          "type": "system",
          "content": "You are a helpful customer service agent."
        }
      ]
    }
  ],
  "metadata_insights_schema": {
    "order_number": "Extract the order number if mentioned"
  },
  "tags_options": [
    "complaint", "inquiry", "positive", "negative"
  ],
  "categories": [
    {
      "name": "Politeness",
      "description": "Measure of agent's politeness"
    }
  ]
}'

This request will return a treasure trove of insights about your conversation, including:

  • Tags that categorize the conversation
  • Metadata extracted based on your schema
  • Insights about your agents’ performance

​
Step 3: Retrieve Conversation Details

Want to take a closer look at a specific conversation? No problem! You can easily fetch the details of any conversation you’ve analyzed.

Here’s how:

curl --request GET \
  --url https://kategory-api-production.up.railway.app/api/conversations/convo456 \
  --header 'x-api-key: YOUR_ACCESS_TOKEN_HERE'

Just replace ‘convo456’ with the ID of the conversation you want to examine.

​
Step 4: Get to Know Your Agents

Curious about how a particular agent is performing? We’ve got you covered there too. You can pull up detailed insights about any agent in your system.

Here’s the command:

curl --request GET \
  --url https://kategory-api-production.up.railway.app/api/agents/agent789 \
  --header 'x-api-key: YOUR_ACCESS_TOKEN_HERE'

Replace ‘agent789’ with the ID of the agent you’re interested in.

​
What’s Next? Exploring and Expanding

Now that you’ve got the basics down, here are some ideas for your next steps:

  1. Dive Deep into Conversations: Take some time to explore the structure of the conversations you’ve analyzed. What patterns do you see? What surprises you?

  2. Get to Know Your Agents: Examine the details of different agents. How do their performances compare? Are there areas where some excel while others might need improvement?

  3. Experiment with Analysis: Try analyzing different types of conversations. How do the insights change based on the content? Play around with different metadata schemas and tag options to see what valuable information you can extract.

  4. Integrate and Automate: Once you’re comfortable with the API, consider integrating it into your existing systems. Could you automate the analysis of all your customer service interactions? What about using the insights to route conversations or provide real-time feedback to agents?

Remember, the key to mastering Vambe Kategor is experimentation and iteration. Start simple, and gradually incorporate more complex scenarios as you become more familiar with the API’s capabilities.

And don’t forget – always replace ‘YOUR_ACCESS_TOKEN_HERE’ with your actual API key in all requests. Security first!

Happy analyzing! If you have any questions or need further clarification, don’t hesitate to reach out. We’re here to help you make the most of Vambe Kategor.

Create a new organization