Deciding Actions
Decision matrices for picking insight types (funnel, retention, semantic, segmentation, SQL), task types, and discovery actions. Use when choosing types or whether to create, update, or skip discoveries.
Exploring Data
Explores Altertable catalogs, schemas, semantic models, tables, and columns. Use when asking about available data, data structure, connections, or sources before querying.
Querying Lakehouse
Writes, validates, optimizes, and executes DuckDB SQL against the Altertable lakehouse. Use when analyzing data, aggregating metrics, building reports, or querying catalogs and external connections.
Using Memory
Stores and retrieves agent memories for context persistence. Use when saving findings, recalling past analysis, or searching for relevant context.
<lowercase-hyphenated-name> # 1-64 chars, lowercase alphanumeric and hyphens, must match directory name
<what it does and when to use it>" # 1-1024 chars, third-person, include trigger keywords
Configuring Tasks
Configures scheduled AI tasks that analyze Insights and Dashboards. Use for anomaly detection, forecasting, alerts, or recurring automated monitoring.
Ask
Routes user queries to the best-fit Altertable skill. Use when unsure which Altertable skill applies to a request.
Managing Discoveries
Manages the discovery approval workflow. Use when handling discovery reviews, approval states, user feedback, or discovery lifecycle.
Evaluating Skills
Evaluates and creates agent skills following best practices. Use when reviewing, writing, or refactoring skills, or asking about skill structure, format, or specification.
Tracking Events
Works with Altertable product analytics events, user identification, and aliasing. Use when tracking events, identifying users, managing traits, or resolving identities.
Forecasting Timeseries
Analyzes time series for trends, anomalies, and forecasts. Use when detecting spikes or drops, predicting future values, or finding unusual patterns over time.
Analyzing Insights
Interprets Insight data to identify patterns, anomalies, and trends. Use when analyzing visualizations, extracting findings, or explaining patterns in graphs.
Building Segments
Builds segmentation insights with filters, dimensions, and breakdowns. Use when segmenting users, comparing event metrics by properties, building cohorts, or defining audiences.
Creating Discoveries
Creates Altertable discoveries from meaningful findings. Use when analysis finds a change, anomaly, root cause, recommendation, warning, or contextual finding that should notify users and enter review.
Analyzing Web Traffic
Analyzes web analytics traffic patterns and user behavior. Use when asked about pageviews, sessions, traffic sources, or website user behavior.
Understanding Platform
Explains Altertable platform concepts and architecture. Use when asking what Altertable is or how agents, discoveries, memories, insights, and dashboards fit together.
Creating Insights
Creates, drafts, renders, and saves Altertable insights. Use when generating findings, creating visualizations, or saving and sharing analysis results.
Analyzing Funnels
Creates and analyzes conversion funnels. Use when analyzing user journeys, drop-off points, onboarding, checkout, or multi-step flows.