- SENTIMENT
- TOPICS
- RAW DATA
- HUMAN
Short answer
How can I use my AI to label customer feedback?
Your AI calls your custom MonkeyLearn classifiers to assign sentiment and topic labels to any text you provide. This turns raw comments into structured data. Here is how the process works.
Data outcomes
Where your data lands.
The AI sorts every piece of text into specific buckets based on your custom logic.
SENTIMENT
Mood detection
The AI identifies if a comment is positive, negative, or neutral. You get a clear view of customer satisfaction levels.
TOPICS
Subject grouping
Text gets tagged with specific categories like pricing or usability. This helps you see exactly what people are talking about.
RAW DATA
Unlabeled text
Any text that doesn't match your specific classifier rules stays as raw, unlabelled input. You can review these manually to refine your models.
HUMAN
Manual review
Low confidence scores or edge cases are flagged for you. You decide if the AI's classification was right or if the model needs tuning.
The workflow
What your AI does when text arrives.
The AI handles the heavy lifting of reading and tagging, so you don't have to manually scan every line.
Find your models
The AI looks up your available MonkeyLearn classifiers to see what it's capable of labeling.
list_classifiersAnalyze the text
The AI sends your raw feedback through the selected classifier to extract labels.
classify_textVerify the labels
The AI checks the output against your requirements to ensure the sentiment and topics are captured.
classify_textOrganize the results
The AI presents the final labeled data in a format you can immediately use for reporting.
classify_text
Try it
Copy these to start.
Use these prompts to kick off the classification process.
Starting points
Swap out the bracketed text for your actual data sources like a Google Sheet or a CSV file.
MonkeyLearn Connector
You're all set. Choose your MCP client and follow the setup instructions.
https://edge.vinkius.com/vk_preview_ajv6syROl8nKEZz1ZGobS0MBFBO5sLwE0cSqFWQ2/mcpClaude Desktop
Follow the steps below to connect in seconds.
- 1In Claude Desktop, open Settings → Connectors.
- 2Click “Add custom connector” and paste the connector link above as the remote MCP server URL.
- 3Click Add and start a new chat — MonkeyLearn capabilities are ready to use.
{
"mcpServers": {
"monkeylearn-mcp": {
"url": "https://edge.vinkius.com/vk_preview_ajv6syROl8nKEZz1ZGobS0MBFBO5sLwE0cSqFWQ2/mcp"
}
}
}Classify the feedback in my 'Customer_Comments' Google Sheet using my sentiment classifier.
Look at the latest 50 rows in my support ticket export and label the topics.
Run my 'Product_Feedback' CSV through the topic classifier and tell me the most common issue.
Use my sentiment classifier to check the latest messages in my Slack feedback channel.
Claude
ChatGPT
Cursor
VS Code
Windsurf
Claude Code
JetBrains
Cline
Start here
Connect MonkeyLearn once, then ask.
Just link your account once. Your credentials stay encrypted, and you can start classifying text immediately through your AI client.
Connect MonkeyLearn to your AIFAQ
How this task behaves.
- 01
Can the AI create new classifiers?
No. The AI can only use the classifiers you have already built and saved in MonkeyLearn.
- 02
Will the AI change my existing MonkeyLearn models?
No. The AI only reads your classifiers to perform labeling; it cannot edit or delete your models.
- 03
Does the AI automatically update my MonkeyLearn dashboard?
The AI performs the classification, but it does not push data back into your MonkeyLearn dashboard unless you specifically ask it to write to a destination tool.
- 04
Can I use multiple classifiers at once?
Yes. You can ask your AI to run the same text through different classifiers for sentiment, topics, or any other custom labels you've made.
- 05
What happens if the AI isn't sure about a label?
The AI will report the classification it finds, but you should always review results where the confidence score is low.
More questions about MonkeyLearn? See everything the MonkeyLearn Connector can do
Connect MonkeyLearn to Claude, Cursor, ChatGPT & more
