- AUDIT
- DATA
- RECORDS
- HUMAN
Short answer
How can I log user behavior using my AI?
You tell your agent what happened, and it uses the track_event tool to push that data to your Dashly audit trail. This turns your conversation into a permanent record of user activity. You'll see how the data flows from your chat to your logs below.
Where your data lands.
Event destinations.
Every event you describe ends up in your behavioral audit trail.
AUDIT
Event logs populated
The AI uses track_event to write the specific action to your trail. You get a clean record of what the user did.
DATA
Structured event properties
Your agent maps your description to specific event properties. This keeps your behavioral data organized and searchable.
RECORDS
User action history
The AI links the event to the correct user context. You'll have a chronological history of specific interactions.
HUMAN
Manual review needed
The AI cannot decide which events are important enough to log. You must tell the agent when a specific action warrants a record.
The workflow
What your AI does when an event occurs.
The agent acts as the bridge between your conversation and your event stream.
Interpret the action
Your agent listens to your description of a user interaction and identifies the core action being performed.
track_eventExtract properties
The agent pulls specific details like button IDs or page names from your text to use as event metadata.
track_eventExecute the log
The agent calls the tool to send the formatted event data to your Dashly account.
track_eventConfirm completion
The agent tells you the event was successfully recorded in the audit trail.
track_event
Try it
Copy these to start.
Use these prompts to trigger event logging immediately.
Starting points
Replace the bracketed text with your actual event names or user details.
Dashly Connector
You're all set. Choose your MCP client and follow the setup instructions.
https://edge.vinkius.com/vk_preview_mKWQpA9wC1T0LWCyaHbWmDACt9xOoNW8yC32afyb/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 — Dashly capabilities are ready to use.
{
"mcpServers": {
"dashly-mcp": {
"url": "https://edge.vinkius.com/vk_preview_mKWQpA9wC1T0LWCyaHbWmDACt9xOoNW8yC32afyb/mcp"
}
}
}Log a 'button_click' event for the user who just signed up in the dashboard.
Track a custom event called 'checkout_completed' for the current session.
Record that a user viewed the pricing page as a 'page_view' event.
Log a 'file_upload' event for the user in the project settings.
Claude
ChatGPT
Cursor
VS Code
Windsurf
Claude Code
JetBrains
Cline
Start here
Connect Dashly once, then ask.
One click connects your agent to Dashly. Your login credentials stay encrypted and secure on our side.
Connect Dashly to your AIFAQ
How this task behaves.
- 01
Can the AI log events automatically without me asking?
No. The AI only logs events when you explicitly tell it to or when it is part of a specific instruction you've given.
- 02
Can the AI delete old events from my audit trail?
No. The track_event tool only allows for creating new records. It cannot modify or delete existing logs.
- 03
Does the AI decide what the event name should be?
The AI will suggest a name based on your description, but you should specify the exact event name you want to ensure your data stays consistent.
- 04
Can I send custom properties with the event?
Yes. You can describe the specific details you want to include, and the agent will include them in the event payload.
- 05
Will this work in any AI client?
Yes, it works in any MCP-compatible client like Claude, Cursor, or Windsurf once you have connected Dashly via Vinkius.
More questions about Dashly? The Connector page answers them. See everything the Dashly Connector can do
Connect Dashly to Claude, Cursor, ChatGPT & more
