Classifying Prompt Patterns in LLM Logs
Use AI-generated columns to categorize unstructured fields in your logs and understand what your system is actually doing.
Overview
LLM logs often contain free-text system prompts that are hard to analyze at scale. In this example, we load a large conversation dataset (Orca), use Hyperparam's AI agent to classify each system prompt into a category, and review the distribution of prompt types across the dataset.

Steps
- Load the log dataset
- Examine the system prompts
Review the
system_promptcolumn. These are the instructions each conversation was given, but as free text they're hard to analyze in aggregate. - Classify with AI
In chat, request: "create a new column that categorizes the system prompt"
The agent analyzes each system prompt and generates categories (e.g., "Education/Tutor", "General Assistant", "Information retrieval/QA"). A new
system_prompt_categorycolumn appears. - Review the distribution
Scroll through rows to verify category assignments. Sort or create a view to see which prompt patterns dominate your dataset.
- Export the results
Export the dataset with the new
system_prompt_categorycolumn included. Export processes the full 100k+ dataset.
Expected Results
- Categorical column:
system_prompt_categoryclassifying each system prompt - Pattern visibility: See which prompt types dominate and which are rare
- Actionable metadata: Filter to specific prompt categories, compare behavior across categories, or identify prompt patterns that correlate with failures
Other Use Cases
- Dataset Discovery - Use natural language to search and discover datasets
- Patient Data Workflow - Extract, filter, and export structured medical data
- Quality Filtering - Remove low-quality responses from datasets
- Deep Research — Multi-step AI workflow for dataset research and model comparison