Skill Directory
Generative Skills
Skill | Description | Mini Chat | Full Chat |
Searches a specific column based on the userβs input to find relevant data. Example: "Find me confused inputs." | β | β | |
Searches across the entire table to identify patterns, anomalies, or outliers. Example: "Find inputs that reference pricing that are hallucinated." | β | β | |
Generates query filters based on natural language commands. Example: "Filter by input contains SDK." | β | β | |
Provides suggestions for search results and finds patterns in the data. Example: "What are the top 5 types of questions asked?" | β | β | |
Writes a tailored eval for your application based on specified goals or data analysis. | β | β | |
Analyzes responses in the retrieval process, ensuring relevance and accuracy, offering improvements. | β | β | |
Optimizes prompts to enhance response quality or address specific issues. | β | β | |
Assesses and summarizes evaluation metrics, providing suggestions for enhancing performance. | β | β |
Tabular Skills
Skill | Description | Full Chat | Mini Chat |
Provides a high-level analysis of model performance, including trends over time, prediction volumes, and drift. Best for general inquiries, not suited for detailed debugging. | β | β | |
Analyzes model performance across different cohorts or slices of data, identifying poorly performing segments. Provides insights into behavior over a specific period. | β | β | |
Pinpoints sudden input quality issues by examining features and tags for drift. Compares current distributions to a baseline to detect significant shifts. | β | β | |
Analyzes input data to report the percentage of missing data in features and tags, highlighting any sudden spikes or changes that could impact model inputs. | β | β | |
Assists in debugging issues by analyzing dataset metrics and focusing on specific dimensions. Identifies critical changes and provides actionable suggestions. | β | β | |
Analyzes a dimensionβs distribution to understand shifts in percentage over time. | β | β | |
Analyzes changes in the cardinality of features and tags over time, highlighting unusual variations that may indicate data quality issues. | β | β |
Last updated