diff --git a/docs/docs/pages/advanced/custom-clients.mdx b/docs/docs/pages/advanced/custom-clients.mdx index 8b553f96..af6d71ad 100644 --- a/docs/docs/pages/advanced/custom-clients.mdx +++ b/docs/docs/pages/advanced/custom-clients.mdx @@ -1,3 +1,8 @@ +--- +title: Advanced Custom Client Configuration +description: Learn advanced techniques for configuring custom LLM clients with Scenario. Explore Azure API Gateway integration, custom OpenAI clients with headers and query parameters, and global ModelConfig settings for enterprise deployments. +--- + import AzureExample from "../_generated/examples/test_azure_api_gateway.mdx"; # Custom Clients [Advanced configuration for custom LLM clients and parameters] diff --git a/docs/docs/pages/agent-integration.mdx b/docs/docs/pages/agent-integration.mdx index e2b60eec..fa7f528b 100644 --- a/docs/docs/pages/agent-integration.mdx +++ b/docs/docs/pages/agent-integration.mdx @@ -1,6 +1,6 @@ --- title: Integrate Any AI Agent Framework -description: Integrate your agent with Scenario's AgentAdapter interface. Works with any framework - LangGraph, CrewAI, Mastra, OpenAI, custom agents. +description: Learn how to integrate your AI agent with Scenario's AgentAdapter interface. Framework-agnostic guide supporting LangGraph, CrewAI, Mastra, OpenAI, Pydantic AI, and custom agent implementations. Works with any LLM or agent architecture. --- import { RefLink } from "../components/RefLink"; diff --git a/docs/docs/pages/agent-integration/agentkit.mdx b/docs/docs/pages/agent-integration/agentkit.mdx index e3eadad9..6e1859bf 100644 --- a/docs/docs/pages/agent-integration/agentkit.mdx +++ b/docs/docs/pages/agent-integration/agentkit.mdx @@ -1,3 +1,8 @@ +--- +title: Test Inngest AgentKit Agents +description: Learn how to test agents built with Inngest's AgentKit using Scenario. Complete guide to validating durable execution, workflow orchestration, stateful agent behavior, event-driven workflows, and multi-agent systems with comprehensive automated testing. +--- + import { RefLink } from "../../components/RefLink"; # Inngest AgentKit Integration [Learn how to integrate AgentKit agents with the Scenario testing framework] diff --git a/docs/docs/pages/agent-integration/agno.mdx b/docs/docs/pages/agent-integration/agno.mdx index 73580f53..06032be4 100644 --- a/docs/docs/pages/agent-integration/agno.mdx +++ b/docs/docs/pages/agent-integration/agno.mdx @@ -1,6 +1,6 @@ --- title: Test Agno Agents -description: Test Agno framework agents. Validate agent workflows, tool usage, and multi-step reasoning with simulation-based testing. +description: Learn how to test Agno framework agents with Scenario testing platform. Complete guide to validating agent workflows, tool usage, multi-step reasoning, and conversation history management with comprehensive automated testing. --- import { RefLink } from "../../components/RefLink"; diff --git a/docs/docs/pages/agent-integration/crewai.mdx b/docs/docs/pages/agent-integration/crewai.mdx index 9936fc32..d31202a4 100644 --- a/docs/docs/pages/agent-integration/crewai.mdx +++ b/docs/docs/pages/agent-integration/crewai.mdx @@ -1,6 +1,6 @@ --- title: Test CrewAI Multi-Agent Systems -description: Test CrewAI crews and multi-agent systems. Validate crew behavior, task delegation, inter-agent communication with automated simulations. +description: Learn how to test CrewAI crews and multi-agent systems with Scenario. Complete guide to validating crew behavior, task delegation, inter-agent communication, and collaborative workflows with automated simulations and comprehensive testing. --- import { RefLink } from "../../components/RefLink"; diff --git a/docs/docs/pages/agent-integration/google-adk.mdx b/docs/docs/pages/agent-integration/google-adk.mdx index 40f7c6d0..d7d9824c 100644 --- a/docs/docs/pages/agent-integration/google-adk.mdx +++ b/docs/docs/pages/agent-integration/google-adk.mdx @@ -1,3 +1,8 @@ +--- +title: Test Google Agent Development Kit (ADK) Agents +description: Learn how to test Google Agent Development Kit (ADK) agents with Scenario. Complete guide to validating Google ADK agent behavior, tool interactions, session management, and Google Cloud integration with comprehensive automated testing. +--- + import { RefLink } from "../../components/RefLink"; # Google ADK Integration [Learn how to integrate Google ADK agents with the Scenario testing framework] diff --git a/docs/docs/pages/agent-integration/https.mdx b/docs/docs/pages/agent-integration/https.mdx index 3b85c06f..e1e5b5ca 100644 --- a/docs/docs/pages/agent-integration/https.mdx +++ b/docs/docs/pages/agent-integration/https.mdx @@ -1,6 +1,6 @@ --- title: Test Agents via HTTPS Endpoints -description: Test AI agents deployed as HTTP/HTTPS services. Learn how to integrate REST APIs and production-deployed agents with Scenario testing framework. +description: Learn how to test AI agents deployed as HTTP/HTTPS services and REST APIs with Scenario. Complete integration guide for testing production-deployed agents, microservices, and serverless functions with blackbox testing methodology. --- import { RefLink } from "../../components/RefLink"; diff --git a/docs/docs/pages/agent-integration/langgraph.mdx b/docs/docs/pages/agent-integration/langgraph.mdx index 0a68d0e4..27324d4a 100644 --- a/docs/docs/pages/agent-integration/langgraph.mdx +++ b/docs/docs/pages/agent-integration/langgraph.mdx @@ -1,6 +1,6 @@ --- title: Test LangGraph Agents -description: Complete guide to testing LangGraph agents. Handle streaming responses, state management, checkpointers, and tool calls in your LangGraph agent tests. +description: Learn how to test LangGraph agents comprehensively with Scenario. Complete guide covering streaming responses, state management, checkpointers, tool calls, and complex graph workflows. Test your LangGraph agents end-to-end with automated simulations. --- import { RefLink } from "../../components/RefLink"; diff --git a/docs/docs/pages/agent-integration/litellm.mdx b/docs/docs/pages/agent-integration/litellm.mdx index f54712eb..88ea02da 100644 --- a/docs/docs/pages/agent-integration/litellm.mdx +++ b/docs/docs/pages/agent-integration/litellm.mdx @@ -1,6 +1,6 @@ --- title: Test LiteLLM Agents - Multi-Provider Testing -description: Test agents using LiteLLM with any LLM provider. Validate behavior across OpenAI, Anthropic, Azure, AWS Bedrock, and 100+ models. +description: Learn how to test agents built with LiteLLM across any LLM provider using Scenario. Comprehensive testing guide for validating agent behavior across OpenAI, Anthropic, Azure, AWS Bedrock, and 100+ supported models with unified interface testing. --- import { RefLink } from "../../components/RefLink"; diff --git a/docs/docs/pages/agent-integration/mastra.mdx b/docs/docs/pages/agent-integration/mastra.mdx index 104f45f5..a4fb67a6 100644 --- a/docs/docs/pages/agent-integration/mastra.mdx +++ b/docs/docs/pages/agent-integration/mastra.mdx @@ -1,6 +1,6 @@ --- title: Test Mastra Agents -description: Test Mastra framework agents. Validate workflows, tool integration, memory, and agent orchestration with simulation-based testing. +description: Learn how to test Mastra framework agents comprehensively with Scenario. Complete guide to validating agent workflows, tool integration, memory management, and agent orchestration with simulation-based testing and automated evaluation. --- import { RefLink } from "../../components/RefLink"; diff --git a/docs/docs/pages/agent-integration/openai.mdx b/docs/docs/pages/agent-integration/openai.mdx index d1f512bc..334bcb24 100644 --- a/docs/docs/pages/agent-integration/openai.mdx +++ b/docs/docs/pages/agent-integration/openai.mdx @@ -1,6 +1,6 @@ --- title: Test OpenAI Assistants & Function Calling -description: Test OpenAI Assistant API, function calling, and custom OpenAI agents. Validate tool usage and multi-turn conversations. +description: Learn how to test OpenAI Assistants API, function calling, and custom OpenAI agents with Scenario. Complete guide to validating tool usage, multi-turn conversations, and OpenAI agent behavior with automated testing and user simulation. --- import { RefLink } from "../../components/RefLink"; diff --git a/docs/docs/pages/agent-integration/pydantic-ai.mdx b/docs/docs/pages/agent-integration/pydantic-ai.mdx index a795ef13..b4022d96 100644 --- a/docs/docs/pages/agent-integration/pydantic-ai.mdx +++ b/docs/docs/pages/agent-integration/pydantic-ai.mdx @@ -1,6 +1,6 @@ --- title: Test Pydantic AI Agents -description: Test Pydantic AI agents with type-safe validation. Verify structured outputs, tool calls, and agent behavior with Scenario. +description: Learn how to test Pydantic AI agents with type-safe validation using Scenario. Complete guide to verifying structured outputs, tool calls, conversation history management, and agent behavior with comprehensive testing patterns. --- import { RefLink } from "../../components/RefLink"; diff --git a/docs/docs/pages/basics/cache.mdx b/docs/docs/pages/basics/cache.mdx index 6f29e1df..2c0466c4 100644 --- a/docs/docs/pages/basics/cache.mdx +++ b/docs/docs/pages/basics/cache.mdx @@ -1,6 +1,6 @@ --- title: Caching for Deterministic Agent Tests -description: Make scenario tests deterministic and faster with LLM call caching. Ensure consistent results across test runs while improving execution speed. +description: Learn how to make scenario tests deterministic and faster with LLM call caching. Comprehensive guide to ensuring consistent test results across test runs while dramatically improving execution speed and reducing API costs. --- import { RefLink } from "../../components/RefLink"; diff --git a/docs/docs/pages/basics/concepts.mdx b/docs/docs/pages/basics/concepts.mdx index e60192fa..538191eb 100644 --- a/docs/docs/pages/basics/concepts.mdx +++ b/docs/docs/pages/basics/concepts.mdx @@ -1,6 +1,6 @@ --- title: Core Concepts -description: Learn scenarios, user simulators, judge agents, and scripted flows. Master the building blocks of simulation-based agent testing. +description: Master the building blocks of simulation-based agent testing with Scenario. Learn about scenarios, user simulators, judge agents, and scripted flows. Complete guide to understanding how these components work together for comprehensive AI agent testing. --- import { RefLink } from "../../components/RefLink"; diff --git a/docs/docs/pages/basics/configuration.mdx b/docs/docs/pages/basics/configuration.mdx index d89b8de2..d8ca9c2e 100644 --- a/docs/docs/pages/basics/configuration.mdx +++ b/docs/docs/pages/basics/configuration.mdx @@ -1,6 +1,6 @@ --- title: Configuration - Environment Variables & Models -description: Configure Scenario with environment variables, model settings, logging, and test runner integration for Python and TypeScript. +description: Learn how to configure Scenario with environment variables, model settings, logging levels, and test runner integration. Complete setup guide for both Python and TypeScript implementations with examples for all configuration methods. --- import { Callout } from "vocs/components"; diff --git a/docs/docs/pages/basics/custom-clients.mdx b/docs/docs/pages/basics/custom-clients.mdx index 207d6d9a..b064f111 100644 --- a/docs/docs/pages/basics/custom-clients.mdx +++ b/docs/docs/pages/basics/custom-clients.mdx @@ -1,3 +1,8 @@ +--- +title: Custom LLM Clients - Advanced Configuration Guide +description: Learn how to configure custom LLM clients and parameters for Scenario's built-in agents. Complete guide for integrating Azure API Gateway, custom OpenAI clients, and advanced LiteLLM parameters with UserSimulatorAgent and JudgeAgent. +--- + # Custom Clients [Advanced configuration for custom LLM clients and parameters] For advanced use cases, you can pass custom clients and additional parameters to Scenario's built-in agents. diff --git a/docs/docs/pages/basics/debug-mode.mdx b/docs/docs/pages/basics/debug-mode.mdx index e4468099..b8e65aae 100644 --- a/docs/docs/pages/basics/debug-mode.mdx +++ b/docs/docs/pages/basics/debug-mode.mdx @@ -1,6 +1,6 @@ --- title: Debug Mode - Interactive Agent Debugging -description: Step through scenarios interactively. Inspect agent responses, intervene with custom inputs, and debug complex conversations in real-time. +description: Learn how to debug AI agents interactively with Scenario's debug mode. Step through scenarios, inspect agent responses, intervene with custom inputs, and debug complex multi-turn conversations in real-time for faster development. --- # Debug Mode [Step through scenarios interactively] diff --git a/docs/docs/pages/basics/scripted-simulations.mdx b/docs/docs/pages/basics/scripted-simulations.mdx index 9093bd93..c013951c 100644 --- a/docs/docs/pages/basics/scripted-simulations.mdx +++ b/docs/docs/pages/basics/scripted-simulations.mdx @@ -1,6 +1,6 @@ --- title: Scripted Simulations - Precise Control -description: Control exact conversation flow with scripted simulations. Orchestrate agent interactions, custom assertions, and deterministic test scenarios. +description: Master scripted simulations for precise control over conversation flow in agent tests. Learn how to orchestrate agent interactions, add custom assertions, implement conditional logic, and create deterministic test scenarios with complete control. --- import { RefLink } from "../../components/RefLink"; diff --git a/docs/docs/pages/basics/test-runner-integration.mdx b/docs/docs/pages/basics/test-runner-integration.mdx index cf982c0b..2dd4f6a0 100644 --- a/docs/docs/pages/basics/test-runner-integration.mdx +++ b/docs/docs/pages/basics/test-runner-integration.mdx @@ -1,6 +1,6 @@ --- title: Test Runner Integration - Vitest, Jest, Pytest -description: Integrate Scenario with popular test runners. Setup guides for Vitest, Jest, and pytest with rich scenario reporting. +description: Learn how to integrate Scenario with popular test runners for seamless testing workflows. Complete setup guides for Vitest, Jest, and pytest with rich scenario reporting, CI/CD integration, and best practices for both Python and TypeScript projects. --- # Test Runner Integration diff --git a/docs/docs/pages/basics/writing-scenarios.mdx b/docs/docs/pages/basics/writing-scenarios.mdx index 688f9b7d..59696fb2 100644 --- a/docs/docs/pages/basics/writing-scenarios.mdx +++ b/docs/docs/pages/basics/writing-scenarios.mdx @@ -1,6 +1,6 @@ --- title: Writing Effective Agent Test Scenarios -description: Best practices for creating robust agent tests. Write clear descriptions, criteria, and assertions for reliable AI agent testing across frameworks. +description: Learn best practices for creating robust and maintainable agent test scenarios. Comprehensive guide covering clear descriptions, evaluation criteria, custom assertions, and testing strategies for reliable AI agent testing across all frameworks. --- import { RefLink } from "../../components/RefLink"; diff --git a/docs/docs/pages/best-practices/domain-driven-tdd.mdx b/docs/docs/pages/best-practices/domain-driven-tdd.mdx index 5d936ea0..a76a3a3e 100644 --- a/docs/docs/pages/best-practices/domain-driven-tdd.mdx +++ b/docs/docs/pages/best-practices/domain-driven-tdd.mdx @@ -1,6 +1,6 @@ --- title: Domain-Driven TDD - Build Agents with Test-First Development -description: Use TDD and Domain-Driven Design principles to build AI agents. Write scenarios in business language first, implement minimally, then refactor to reveal domain concepts. +description: Learn how to combine Test-Driven Development with Domain-Driven Design principles for building robust AI agents. Write scenarios in business language first, implement minimally with red-green-refactor cycle, then refactor to reveal domain concepts and improve agent architecture. --- # Domain-Driven TDD [Using scenarios to drive implementation] diff --git a/docs/docs/pages/best-practices/the-agent-testing-pyramid.mdx b/docs/docs/pages/best-practices/the-agent-testing-pyramid.mdx index b690c4b9..4db7ab47 100644 --- a/docs/docs/pages/best-practices/the-agent-testing-pyramid.mdx +++ b/docs/docs/pages/best-practices/the-agent-testing-pyramid.mdx @@ -1,6 +1,6 @@ --- title: The Agent Testing Pyramid -description: Master the agent testing pyramid. Balance unit tests, evals, and simulations for comprehensive AI agent quality assurance and reliable deployments. +description: Master the agent testing pyramid for comprehensive AI agent quality assurance. Learn how to balance unit tests, evals, and simulations for reliable deployments. Three-layered approach to systematic agent testing inspired by traditional testing pyramids. --- import { Authors } from "vocs/components"; diff --git a/docs/docs/pages/best-practices/the-vibe-eval-loop.mdx b/docs/docs/pages/best-practices/the-vibe-eval-loop.mdx index c98d5b3e..6c7864bd 100644 --- a/docs/docs/pages/best-practices/the-vibe-eval-loop.mdx +++ b/docs/docs/pages/best-practices/the-vibe-eval-loop.mdx @@ -1,6 +1,6 @@ --- title: The Vibe-Eval Loop - TDD for AI Agents -description: Rapidly iterate on agent behavior with the vibe-eval loop. Combine human intuition with automated testing for faster, more reliable agent development. +description: Learn the vibe-eval loop methodology for rapidly iterating on agent behavior. Combine human intuition with automated testing, capture edge cases systematically, and scale beyond POCs with a TDD-inspired workflow for faster and more reliable agent development. --- import { Authors } from "vocs/components"; diff --git a/docs/docs/pages/community-support.mdx b/docs/docs/pages/community-support.mdx index 5ecbb173..05013ac2 100644 --- a/docs/docs/pages/community-support.mdx +++ b/docs/docs/pages/community-support.mdx @@ -1,6 +1,6 @@ --- title: Community & Support -description: Join Scenario community on Discord for help with agent testing. Connect with developers, share patterns, and get support for LangGraph, CrewAI, and custom agents. +description: Join the Scenario community on Discord for help with AI agent testing. Connect with developers, share testing patterns, get technical support for LangGraph, CrewAI, and custom agents. Access documentation, file issues, and stay updated on releases. --- # Community & Support [Join Scenario community to connect with other users, get help, and explore the agent development ecosystem] diff --git a/docs/docs/pages/examples/multimodal/multimodal-files.mdx b/docs/docs/pages/examples/multimodal/multimodal-files.mdx index 78acae97..1a971f3d 100644 --- a/docs/docs/pages/examples/multimodal/multimodal-files.mdx +++ b/docs/docs/pages/examples/multimodal/multimodal-files.mdx @@ -1,3 +1,8 @@ +--- +title: Testing File Analysis Agents - PDF, CSV & Document Processing +description: Learn how to test AI agents that analyze and process files like PDFs, CSVs, and other documents. Comprehensive guide for building Scenario tests where agents parse user-provided files and respond appropriately. +--- + # Multimodal File Analysis (Coming Soon) This page will demonstrate how to build Scenario tests where the user provides **files** (PDF, CSV, etc.) as part of the conversation and the agent must parse and respond appropriately. diff --git a/docs/docs/pages/examples/multimodal/multimodal-image-generation.mdx b/docs/docs/pages/examples/multimodal/multimodal-image-generation.mdx index c60fcc2c..8355cc57 100644 --- a/docs/docs/pages/examples/multimodal/multimodal-image-generation.mdx +++ b/docs/docs/pages/examples/multimodal/multimodal-image-generation.mdx @@ -1,3 +1,8 @@ +--- +title: Testing Image Generation Agents - AI Art & Creative AI +description: Learn how to test AI agents that generate images from text prompts. Comprehensive testing guide for evaluating prompt quality, image generation, and creative AI capabilities with automated judge evaluation. +--- + # Multimodal Image Generation (Coming Soon) This page will demonstrate how to build Scenario tests where the agent generates **images from text prompts** and the judge evaluates both the prompt quality and the generated image quality. diff --git a/docs/docs/pages/examples/multimodal/overview.mdx b/docs/docs/pages/examples/multimodal/overview.mdx index c6598c3e..374be01e 100644 --- a/docs/docs/pages/examples/multimodal/overview.mdx +++ b/docs/docs/pages/examples/multimodal/overview.mdx @@ -1,6 +1,6 @@ --- title: Multimodal Agent Testing - Images, Audio, Files -description: Test multimodal AI agents that process images, audio, and files. Learn patterns for testing voice agents, vision agents, and file processing. +description: Learn how to test multimodal AI agents that process images, audio, and files with Scenario. Comprehensive guide covering testing patterns for voice agents, vision agents, file processing, and combined multimodal inputs with automated evaluation. --- # Multimodal Use Cases – Overview diff --git a/docs/docs/pages/examples/testing-remote-agents.mdx b/docs/docs/pages/examples/testing-remote-agents.mdx index 3cbf5940..07915c3f 100644 --- a/docs/docs/pages/examples/testing-remote-agents.mdx +++ b/docs/docs/pages/examples/testing-remote-agents.mdx @@ -1,6 +1,6 @@ --- title: Testing Remote Agents - HTTP Adapter Patterns -description: Learn how to test HTTP-deployed AI agents with Scenario. Adapter patterns for JSON, streaming, SSE, and stateful APIs. Production-ready examples for REST endpoints. +description: Learn how to test HTTP-deployed AI agents comprehensively with Scenario. Complete guide covering adapter patterns for JSON responses, streaming, Server-Sent Events (SSE), and stateful APIs. Production-ready examples and patterns for REST endpoints. --- # Testing Remote Agents [Adapters for HTTP-deployed agents] diff --git a/docs/docs/pages/index.mdx b/docs/docs/pages/index.mdx index 74b714d0..c664a279 100644 --- a/docs/docs/pages/index.mdx +++ b/docs/docs/pages/index.mdx @@ -1,6 +1,6 @@ --- title: Agent Testing Framework -description: Test AI agents with simulation-based testing. LLM-powered user simulators for agent behavior testing, tool calling, and multi-turn conversations. Works with LangGraph, CrewAI, Pydantic AI. +description: Learn how to test AI agents with simulation-based testing using Scenario. LLM-powered user simulators enable comprehensive agent behavior testing, tool calling validation, and multi-turn conversation testing. Works seamlessly with LangGraph, CrewAI, Pydantic AI, and more. --- import { Image } from "../components/Image"; diff --git a/docs/docs/pages/introduction/getting-started.mdx b/docs/docs/pages/introduction/getting-started.mdx index 92c7c926..d603018b 100644 --- a/docs/docs/pages/introduction/getting-started.mdx +++ b/docs/docs/pages/introduction/getting-started.mdx @@ -1,6 +1,6 @@ --- title: Getting Started - Your First Agent Test -description: Build your first AI agent test in 5 minutes. Step-by-step tutorial with user simulators, automated evaluation, and visual debugging for LangGraph, CrewAI, and custom agents. +description: Learn how to build your first AI agent test in 5 minutes with Scenario. Complete step-by-step tutorial covering user simulators, automated evaluation, and visual debugging for LangGraph, CrewAI, and custom agent frameworks. --- import { EmbeddedScript } from "../../components/EmbeddedScript"; diff --git a/docs/docs/pages/introduction/simulation-based-testing.mdx b/docs/docs/pages/introduction/simulation-based-testing.mdx index bb682e4c..c5160922 100644 --- a/docs/docs/pages/introduction/simulation-based-testing.mdx +++ b/docs/docs/pages/introduction/simulation-based-testing.mdx @@ -1,6 +1,6 @@ --- title: Simulation-Based Testing for AI Agents -description: Why simulation-based testing is essential for AI agents. Learn the testing pyramid for agents and how simulations catch edge cases traditional testing misses. +description: Understand why simulation-based testing is essential for AI agents in production. Learn about the agent testing pyramid and discover how simulations catch edge cases, validate stateful behavior, and test multi-turn conversations that traditional testing methods miss. --- # Simulation-Based Testing [Multi-agent applications require a new approach to testing] diff --git a/docs/docs/pages/testing-guides/blackbox-testing.mdx b/docs/docs/pages/testing-guides/blackbox-testing.mdx index c3249a0a..dac14dfb 100644 --- a/docs/docs/pages/testing-guides/blackbox-testing.mdx +++ b/docs/docs/pages/testing-guides/blackbox-testing.mdx @@ -1,6 +1,6 @@ --- title: Blackbox Testing - Test Agents via Public Interfaces -description: Test AI agents through their public interfaces without mocking. Learn how to use HTTP adapters for production-like testing with real databases, authentication, and infrastructure. +description: Learn how to test AI agents through their public interfaces without mocking internal components. Complete guide to using HTTP adapters for production-like testing with real databases, authentication, middleware, and infrastructure - testing exactly how agents run in production. --- # Blackbox Testing [Testing via public interfaces] diff --git a/docs/docs/pages/testing-guides/fixtures.mdx b/docs/docs/pages/testing-guides/fixtures.mdx index d380ac1e..a2e17210 100644 --- a/docs/docs/pages/testing-guides/fixtures.mdx +++ b/docs/docs/pages/testing-guides/fixtures.mdx @@ -1,6 +1,6 @@ --- title: Test Fixtures for Deterministic Agent Tests -description: Create repeatable tests with static fixtures. Use images, audio, and data files for offline-friendly, deterministic agent testing. +description: Learn how to create repeatable, deterministic agent tests with static test fixtures. Complete guide to using images, audio clips, JSON payloads, and data files for offline-friendly testing that ensures consistent results and faster test execution. --- # Fixtures [Static test assets for deterministic scenarios] diff --git a/docs/docs/pages/testing-guides/mocks.mdx b/docs/docs/pages/testing-guides/mocks.mdx index 8a038abb..713760f2 100644 --- a/docs/docs/pages/testing-guides/mocks.mdx +++ b/docs/docs/pages/testing-guides/mocks.mdx @@ -1,6 +1,6 @@ --- title: Mocking External APIs in Agent Tests -description: Mock external dependencies for fast, reliable agent tests. Isolate agent behavior from third-party services with tool mocking patterns. +description: Learn how to mock external dependencies for fast, reliable agent tests. Complete guide to isolating agent behavior from third-party services with tool mocking patterns, database mocking, API service mocking, and testing tool failures for deterministic offline testing. --- import { LanguageTabs } from "../../components/LanguageTabs"; diff --git a/docs/docs/pages/testing-guides/tool-calling.mdx b/docs/docs/pages/testing-guides/tool-calling.mdx index b488277e..f2d7adb0 100644 --- a/docs/docs/pages/testing-guides/tool-calling.mdx +++ b/docs/docs/pages/testing-guides/tool-calling.mdx @@ -1,6 +1,6 @@ --- title: Testing AI Agent Tool Calls & Function Calling -description: Test and validate agent tool usage. Assert on function calls, mock tool responses, verify tool call arguments, and test tool calling flows. +description: Learn how to test and validate AI agent tool usage comprehensively. Complete guide covering assertions on function calls, mocking tool responses, verifying tool call arguments, testing tool calling flows, and validating agent tool selection behavior. --- # Testing Tool Calls in Scenarios diff --git a/docs/docs/pages/visualizations/index.mdx b/docs/docs/pages/visualizations/index.mdx index 1cfb8d53..381f1d34 100644 --- a/docs/docs/pages/visualizations/index.mdx +++ b/docs/docs/pages/visualizations/index.mdx @@ -1,6 +1,6 @@ --- title: Simulation Visualizer - Debug Agent Tests -description: Visualize agent test results with LangWatch. Browse conversations, debug tool calls, share results with your team, and improve agents faster. +description: Learn how to visualize agent test results with LangWatch's simulation visualizer. Browse conversations, debug tool calls, analyze agent behavior, share results with your team, and improve agents faster with visual debugging tools. --- import { Callout } from "vocs/components"; diff --git a/python/scenario/__init__.py b/python/scenario/__init__.py index e9556e71..59483f54 100644 --- a/python/scenario/__init__.py +++ b/python/scenario/__init__.py @@ -1,5 +1,5 @@ """ -Scenario: Agent Testing Framework through Simulation Testing +Access Scenario API root documentation to build simulation-based evaluations and structured AI agent testing flows. Scenario is a comprehensive testing framework for AI agents that uses simulation testing to validate agent behavior through realistic conversations. It enables testing of both diff --git a/python/scenario/agent_adapter.py b/python/scenario/agent_adapter.py index 810ed42f..6a5f840a 100644 --- a/python/scenario/agent_adapter.py +++ b/python/scenario/agent_adapter.py @@ -1,5 +1,5 @@ """ -Agent adapter module for integrating custom agents with the Scenario framework. +Explore the Scenario Python API to integrate custom agents into simulation-based AI agent tests within LangWatch. This module provides the abstract base class that users must implement to integrate their existing agents with the Scenario testing framework. The adapter pattern allows diff --git a/python/scenario/config/__init__.py b/python/scenario/config/__init__.py index 431556c3..6ab34810 100644 --- a/python/scenario/config/__init__.py +++ b/python/scenario/config/__init__.py @@ -1,5 +1,5 @@ """ -Configuration module for Scenario. +Explore Scenario configuration modules to define simulation rules, agent behavior, and evaluation flows for agent testing. This module provides all configuration classes for customizing the behavior of the Scenario testing framework, including model settings, scenario execution diff --git a/python/scenario/config/langwatch.py b/python/scenario/config/langwatch.py index 42661203..e593238e 100644 --- a/python/scenario/config/langwatch.py +++ b/python/scenario/config/langwatch.py @@ -1,5 +1,5 @@ """ -LangWatch configuration for Scenario. +Use LangWatch configuration in Scenario to link agent simulations with observability, evaluations, and AI agent testing. This module provides configuration for LangWatch API integration, including endpoint URLs and authentication credentials. diff --git a/python/scenario/config/model.py b/python/scenario/config/model.py index d8300587..b985140c 100644 --- a/python/scenario/config/model.py +++ b/python/scenario/config/model.py @@ -1,5 +1,5 @@ """ -Model configuration for Scenario. +Configure model settings in Scenario to define underlying LLM behavior for AI agent testing environments. This module provides configuration classes for LLM model settings used by user simulator and judge agents in the Scenario framework. diff --git a/python/scenario/config/scenario.py b/python/scenario/config/scenario.py index fa1abb78..12f31996 100644 --- a/python/scenario/config/scenario.py +++ b/python/scenario/config/scenario.py @@ -1,5 +1,5 @@ """ -Scenario configuration for Scenario. +Access Scenario configuration in Python to define evaluation policies and structured agent testing behavior. This module provides the main configuration class for customizing the behavior of the Scenario testing framework, including execution parameters and debugging options. diff --git a/python/scenario/judge_agent.py b/python/scenario/judge_agent.py index 8abbaeaf..450a0dcd 100644 --- a/python/scenario/judge_agent.py +++ b/python/scenario/judge_agent.py @@ -1,5 +1,5 @@ """ -Judge agent module for evaluating scenario conversations. +Use the Judge Agent module in Scenario to evaluate conversation quality and LLM reasoning during AI agent testing. This module provides the JudgeAgent class, which evaluates ongoing conversations between users and agents to determine if success criteria are met. The judge diff --git a/python/scenario/pytest_plugin.py b/python/scenario/pytest_plugin.py index f05a2b34..34d353d0 100644 --- a/python/scenario/pytest_plugin.py +++ b/python/scenario/pytest_plugin.py @@ -1,5 +1,5 @@ """ -Pytest plugin for Scenario testing library. +Use the Scenario pytest plugin to run simulation-based agent tests directly in your CI pipeline.. This module provides pytest integration for the Scenario framework, including automatic test reporting, debug mode support, and collection of scenario diff --git a/python/scenario/script.py b/python/scenario/script.py index 8010d6b5..2a084d9c 100644 --- a/python/scenario/script.py +++ b/python/scenario/script.py @@ -1,5 +1,5 @@ """ -Scenario script DSL (Domain Specific Language) module. +Use the Scenario script DSL to define simulation flows and evaluate AI agent behavior in structured testing environments.. This module provides a collection of functions that form a declarative language for controlling scenario execution flow. These functions can be used to create diff --git a/python/scenario/user_simulator_agent.py b/python/scenario/user_simulator_agent.py index 5364b59e..cc179152 100644 --- a/python/scenario/user_simulator_agent.py +++ b/python/scenario/user_simulator_agent.py @@ -1,5 +1,5 @@ """ -User simulator agent module for generating realistic user interactions. +Simulate realistic user interactions using Scenario’s user simulator tools for robust agent testing This module provides the UserSimulatorAgent class, which simulates human user behavior in conversations with agents under test. The simulator generates