Superluminal

Converts natural language questions into executable dashboard queries by parsing user intent and mapping it to underlying data schema. The system likely uses LLM-based semantic understanding combined with schema introspection to identify relevant metrics, dimensions, and filters, then generates the appropriate query syntax (SQL, dashboard API calls, or proprietary query language) without requiring users to understand the technical query structure.

Proactively suggests relevant metrics, KPIs, and drill-down paths based on user context and historical query patterns. The system analyzes what questions users ask, what data they access, and their role/team to recommend related metrics they might want to explore, using collaborative filtering or usage-based heuristics combined with domain knowledge about common metric relationships.

Maintains conversational context across multiple turns, allowing users to ask follow-up questions that reference previous queries, results, and implicit context. The system uses conversation history management with state tracking to understand pronouns, relative references ('that metric', 'the previous result'), and implicit drill-down requests, enabling natural dialogue rather than isolated queries.

Automatically discovers and maps dashboard structure, metrics, dimensions, filters, and data relationships by introspecting the connected dashboard platform's API and metadata. The system builds an internal semantic model of available data, metric definitions, and valid query combinations, enabling the LLM to generate accurate queries without manual schema configuration.

Analyzes query results and generates natural language explanations of what the data shows, including trend identification, anomaly detection, and contextual insights. The system compares results against historical baselines, identifies statistically significant changes, and articulates business implications in plain language, helping users understand not just the numbers but their meaning.

Analyzes relationships and correlations between metrics across multiple connected dashboards or data sources, identifying which metrics move together and which are independent. The system likely uses time-series correlation analysis combined with semantic understanding of metric relationships to surface non-obvious connections and help users understand multi-dimensional cause-and-effect relationships in their data.

Translates natural language filter requests into dashboard-specific filter syntax and generates dynamic segmentation queries. When users ask questions like 'show me results for enterprise customers in the US', the system parses the intent, identifies relevant dimensions and values, and constructs the appropriate filter expressions without requiring users to manually select filters from dropdown menus.

Stores and retrieves previously asked questions and analysis patterns, allowing users to reuse and modify past queries without re-asking. The system maintains a searchable library of queries with metadata (intent, results, timestamp, user), enabling users to find similar past analyses and adapt them for new questions, reducing repetitive work.