LogoLogo
AboutBlogLaunch app ↗
v0.20.x
v0.20.x
  • Introduction to AI Testing
  • Welcome to Distributional
  • Motivation
  • What is AI Testing?
  • Stages in the AI Software Development Lifecycle
    • Components of AI Testing
  • Distributional Testing
  • Getting Access to Distributional
  • Learning about Distributional
    • The Distributional Framework
    • Defining Tests in Distributional
      • Automated Production test creation & execution
      • Knowledge-based test creation
      • Comprehensive testing with Distributional
    • Reviewing Test Sessions and Runs in Distributional
      • Reviewing and recalibrating automated Production tests
      • Insights surfaced elsewhere on Distributional
      • Notifications
    • Data in Distributional
      • The flow of data
      • Components and the DAG for root cause analysis
      • Uploading data to Distributional
      • Living in your VPC
  • Using Distributional
    • Getting Started
    • Access
      • Organization and Namespaces
      • Users and Permissions
      • Tokens
    • Data
      • Data Objects
      • Run-Level Data
      • Data Storage Integrations
      • Data Access Controls
    • Testing
      • Creating Tests
        • Test Page
        • Test Drawer Through Shortcuts
        • Test Templates
        • SDK
      • Defining Assertions
      • Production Testing
        • Auto-Test Generation
        • Recalibration
        • Notable Results
        • Dynamic Baseline
      • Testing Strategies
        • Test That a Given Distribution Has Certain Properties
        • Test That Distributions Have the Same Statistics
        • Test That Columns Are Similarly Distributed
        • Test That Specific Results Have Matching Behavior
        • Test That Distributions Are Not the Same
      • Executing Tests
        • Manually Running Tests Via UI
        • Executing Tests Via SDK
      • Reviewing Tests
      • Using Filters
        • Filters in the Compare Page
        • Filters in Tests
    • Python SDK
      • Quick Start
      • Functions
        • login
        • Project
          • create_project
          • copy_project
          • export_project_as_json
          • get_project
          • get_or_create_project
          • import_project_from_json
        • Run Config
          • create_run_config
          • get_latest_run_config
          • get_run_config
          • get_run_config_from_latest_run
        • Run Results
          • get_column_results
          • get_scalar_results
          • get_results
          • report_column_results
          • report_scalar_results
          • report_results
        • Run
          • close_run
          • create_run
          • get_run
          • report_run_with_results
        • Baseline
          • create_run_query
          • get_run_query
          • set_run_as_baseline
          • set_run_query_as_baseline
        • Test Session
          • create_test_session
      • Objects
        • Project
        • RunConfig
        • Run
        • RunQuery
        • TestSession
        • TestRecalibrationSession
        • TestGenerationSession
        • ResultData
      • Experimental Functions
        • create_test
        • get_tests
        • get_test_sessions
        • wait_for_test_session
        • get_or_create_tag
        • prepare_incomplete_test_spec_payload
        • create_test_recalibration_session
        • wait_for_test_recalibration_session
        • create_test_generation_session
        • wait_for_test_generation_session
      • Eval Module
        • Quick Start
        • Application Metric Sets
        • How-To / FAQ
        • LLM-as-judge and Embedding Metrics
        • RAG / Question Answer Example
        • Eval Module Functions
          • Index of functions
          • eval
          • eval.metrics
    • Notifications
    • Release Notes
  • Tutorials
    • Instructions
    • Hello World (Sentiment Classifier)
    • Trading Strategy
    • LLM Text Summarization
      • Setting the Scene
      • Prompt Engineering
      • Integration testing for text summarization
      • Practical considerations
Powered by GitBook

© 2025 Distributional, Inc. All Rights Reserved.

On this page

Was this helpful?

Export as PDF
  1. Learning about Distributional
  2. Defining Tests in Distributional

Knowledge-based test creation

Incorporate your expertise alongside our automated tests

PreviousAutomated Production test creation & executionNextComprehensive testing with Distributional

Was this helpful?

While we expect everyone to use our automated Production test creation capabilities, we also recognize that many users bring significant expertise to their testing experience. Distributional provides you a suite of test creation tools and patterns that match your needs.

Most tests in dbnl are statistically-motivated to better measure and study fundamentally nondeterministic AI-powered apps. Means, percentiles, Kolmogorov-Smirnov, and other statistical entities are provided to allow you to study the behavior of your app as you would like. We provide templates to guide you through our .

The manual test creation process can be configured in any of three locations: in the main web UI , through scattered throughout the web UI, or through the . This gives you the flexibility to systematically control test generation, or quickly respond to insights for which you would like to test in the future.

The core testing capability is supplemented by the ability to define . These filters empower you to test for consistency within subsets of your user base. Filtering also allows you to test for bias in your app and help triage cases of undesired behavior.

Learn more about how to create your own tests .

filters on tests
here
suggested testing strategies
test configuration page
shortcuts to the test drawer
SDK
Menu of common testing strategies that are supported by templates in dbnl.