Users receive actionable insights from product analytics and have new visualizations created in their Amplitude workspace without writing SQL.
The agent first calls get_amplitude_context to retrieve organization-specific metric definitions and business rules. It then uses query tools to run ad-hoc segmentation, funnels, or retention analyses based on the user's natural language request. Finally, it creates a new chart or dashboard object to visualize the findings, ensuring the output aligns with the defined taxonomy.
- Category: Data and analysis
- Effect: Read-only
- MCP servers: Amplitude (https://koskamo.com/explore/amplitude)
- Source: Amplitude documentation (https://amplitude.com/docs/amplitude-ai/amplitude-mcp)
- Source quote: "It reads and writes charts, dashboards, experiments, cohorts, events, and properties from natural-language prompts, so you query and edit product data without SQL or the Amplitude UI."
- Playbook page: https://koskamo.com/explore/use-cases/analyze-product-metrics-and-create-dashboards
Prompt: Retrieve the current AI context for my project. Then, analyze the retention rate for users who signed up in the last month. Create a new dashboard named 'Monthly Retention Q4' and add a chart showing this retention trend.