Analyze Ai Topics

AI Topic Analyzer

You analyze what users ask AI agents about and how well each topic is served — surfacing underserved areas, coverage gaps, and product opportunities from conversation patterns. This is the product intelligence skill that turns AI session data into "what to build next" decisions.

Instructions

Step 1: Get Context and Schema

1. Get context. Call Amplitude:get_context to identify projects and user role.
2. Get AI schema. Call Amplitude:get_agent_analytics_schema with include: ["filter_options", "taxonomy"] to discover available topic models, agent names, and classification values. The schema tells you what topic dimensions exist (e.g., productarea, intent, errordomain) — these vary by project.
3. Determine scope. If the user specifies an agent, time window, or focus area, narrow accordingly. Default: all agents, last 14 days (longer window gives more stable topic distributions).

Step 2: Map the Topic Landscape

Run these in parallel:

1. Topic breakdown with quality. Call Amplitude:query_agent_analytics_metrics with metrics: ["topics"], limit: 50. This returns each topic with session count, average quality score, average sentiment, and failure rate. This is the core dataset.

1. Agent-by-topic matrix. Call Amplitude:query_agent_analytics_sessions with groupBy: ["agent_name", "primary_topic"], limit: 100. This shows which agents handle which topics — and where quality differs by agent for the same topic.

1. Volume trend by topic. Call Amplitude:query_agent_analytics_metrics with metrics: ["volume_timeseries"], interval: "DAY". While this is aggregate, combine it with the topic breakdown to understand whether total volume growth is driven by specific topics.

1. Failure sessions by topic. Call Amplitude:query_agent_analytics_sessions with hasTaskFailure: true, groupBy: ["primary_topic"], limit: 50. This shows which topics have the most failures — a different signal from low quality (failures are hard stops, low quality is soft degradation).

Step 3: Identify Underserved Topics

Score each topic on a 2x2 of volume x quality:

| | High Quality (>0.7) | Low Quality (50) Group similar topics and present the top 20 by volume. Offer to drill into specific clusters on request.

Topics are too generic

If topic labels are broad (e.g., "data question", "help request"), the enrichment model may need tuning. Note this and use conversation search to identify more specific sub-topics manually.

Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

• Author: amplitude
• Source: amplitude/mcp-marketplace
• License: MIT

Install and usage instructions live in the source repository linked above.