# Rasa Documentation

- [Get started with Rasa](https://rasa.com/docs/index.md): Rasa is the agent platform for AI product teams.
- [Developer Quickstart](https://rasa.com/docs/learn/quickstart/pro.md): Fastest happy path to run Rasa, connect MCP tools, and build your first agent.
- [Conversational AI with Language Models](https://rasa.com/docs/learn/concepts/calm.md): (CALM) is an LLM-native approach to building reliable conversational AI.
- [Helping Your Assistant Understand Users](https://rasa.com/docs/learn/concepts/dialogue-understanding.md): Learn more about how Rasa assistants make decisions.
- [Designing the Logic Behind Conversations](https://rasa.com/docs/learn/concepts/dialogue-management.md): Learn more about how to manage dialogue with Rasa
- [Conversation Patterns](https://rasa.com/docs/learn/concepts/conversation-patterns.md): Learn more about how to use the conversation lifecycle to ensure seamless conversations.
- [Custom Actions in Rasa](https://rasa.com/docs/learn/guides/adding-custom-actions.md): Learn more about how to design your assistant
- [Integrate RAG in Rasa](https://rasa.com/docs/learn/guides/integrating-rag.md): Learn more about how to design your assistant
- [Build an Agent with Prompts](https://rasa.com/docs/learn/ai-assisted-development.md): Build a complete Rasa agent feature end-to-end using prompt-driven development and Rasa MCP Tools.
- [Designing Natural and Engaging Conversations](https://rasa.com/docs/learn/best-practices/conversation-design.md): Learn more about how to design your assistant using CALM and Rasa
- [Building a Conversational AI Team](https://rasa.com/docs/learn/best-practices/conversational-ai-teams.md): Learn more about how to set up a conversational AI team
- [Installing on Amazon Web Services (AWS)](https://rasa.com/docs/learn/deployment/aws/aws-playbook-intro.md): This playbook outlines an opinionated, best-practice way to install Rasa Pro and Rasa Studio on AWS. You may wish to adapt steps and configuration to meet your needs or organisational policies as required.
- [Setup](https://rasa.com/docs/learn/deployment/aws/aws-playbook-setup.md): Prerequisites
- [Deploy Infrastructure](https://rasa.com/docs/learn/deployment/aws/aws-playbook-infra.md): Before you begin, ensure you've completed the Setup Steps to set environment variables and clone a repo that this section requires.
- [Configure Your Kubernetes Cluster](https://rasa.com/docs/learn/deployment/aws/aws-playbook-k8s.md): Before you begin, ensure you've completed all the previous sections to deploy required infrastructure and to set environment variables that this section requires.
- [Install Rasa](https://rasa.com/docs/learn/deployment/aws/aws-playbook-rasa.md): Before you begin, ensure you've completed all the previous sections to deploy required infrastructure and to set environment variables that this section requires.
- [Install Rasa Studio](https://rasa.com/docs/learn/deployment/aws/aws-playbook-studio.md): Before you begin, ensure you've completed all of the previous sections to deploy required infrastructure and to set environment variables that this section requires.
- [AWS Cleanup Infrastructure [Optional]](https://rasa.com/docs/learn/deployment/aws/aws-playbook-cleanup.md): Following these steps will delete all of the infrastructure and configuration you have deployed in all the previous steps. You'll need to set the environment variables defined in Setup Steps before you begin.
- [Set Up Your Agent on AWS](https://rasa.com/docs/learn/deployment/aws/aws-playbook-setup-agent.md): Before you begin, ensure you've finished installing Rasa Pro on Amazon Web Services:
- [Installing on Microsoft Azure](https://rasa.com/docs/learn/deployment/azure/azure-playbook-intro.md): This playbook outlines an opinionated, best-practice way to install Rasa Pro and Rasa Studio on Azure. You may wish to adapt steps and configuration to meet your needs or organisational policies as required.
- [Setup](https://rasa.com/docs/learn/deployment/azure/azure-playbook-setup.md): Prerequisites
- [Deploy Infrastructure](https://rasa.com/docs/learn/deployment/azure/azure-playbook-infra.md): Before you begin, ensure you've completed the Setup Steps to set environment variables and clone a repo that this section requires.
- [Configure Your Kubernetes Cluster](https://rasa.com/docs/learn/deployment/azure/azure-playbook-k8s.md): Before you begin, ensure you've completed all of the previous sections to deploy required infrastructure and to set environment variables that this section requires.
- [Install Rasa](https://rasa.com/docs/learn/deployment/azure/azure-playbook-rasa.md): Before you begin, ensure you've completed all of the previous sections to deploy required infrastructure and to set environment variables that this section requires.
- [Install Rasa Studio](https://rasa.com/docs/learn/deployment/azure/azure-playbook-studio.md): Before you begin, ensure you've completed all of the previous sections to deploy required infrastructure and to set environment variables that this section requires.
- [Azure Cleanup Infrastructure [Optional]](https://rasa.com/docs/learn/deployment/azure/azure-playbook-cleanup.md): Following these steps will delete all of the infrastructure and configuration you have deployed in all the previous steps. You'll need to set the environment variables defined in Setup Steps before you begin.
- [Set Up Your Agent on Azure](https://rasa.com/docs/learn/deployment/azure/azure-playbook-setup-agent.md): Before you begin, ensure you've finished installing Rasa Pro on Microsoft Azure:
- [Installing on Google Cloud Platform](https://rasa.com/docs/learn/deployment/gcp/gcp-playbook-intro.md): This playbook outlines an opinionated, best-practice way to install Rasa Pro and Rasa Studio on Google Cloud Platform. You may wish to adapt steps and configuration to meet your needs or organisational policies as required.
- [Setup](https://rasa.com/docs/learn/deployment/gcp/gcp-playbook-setup.md): Prerequisites
- [Deploy Infrastructure](https://rasa.com/docs/learn/deployment/gcp/gcp-playbook-infra.md): Before you begin, ensure you've completed the Setup Steps to set environment variables and clone a repo that this section requires.
- [Configure Your Kubernetes Cluster](https://rasa.com/docs/learn/deployment/gcp/gcp-playbook-k8s.md): Before you begin, ensure you've completed all of the previous sections to deploy required infrastructure and to set environment variables that this section requires.
- [Install Rasa](https://rasa.com/docs/learn/deployment/gcp/gcp-playbook-rasa.md): Before you begin, ensure you've completed all of the previous sections to deploy required infrastructure and to set environment variables that this section requires.
- [Install Rasa Studio](https://rasa.com/docs/learn/deployment/gcp/gcp-playbook-studio.md): Before you begin, ensure you've completed all of the previous sections to deploy required infrastructure and to set environment variables that this section requires.
- [GCP Cleanup Infrastructure [Optional]](https://rasa.com/docs/learn/deployment/gcp/gcp-playbook-cleanup.md): Following these steps will delete all of the infrastructure and configuration you have deployed in all the previous steps. You'll need to set the environment variables defined in Setup Steps before you begin.
- [Set Up Your Agent on GCP](https://rasa.com/docs/learn/deployment/gcp/gcp-playbook-setup-agent.md): Before you begin, ensure you've finished installing Rasa Pro on Google Cloud Platform:
- [Rasa: Code-First AI Agent Framework](https://rasa.com/docs/pro/intro.md): Learn how Rasa combines CALM, large language models, flows, and explicit business logic to build reliable conversational AI agents.
- [Rasa Tutorial](https://rasa.com/docs/pro/tutorial.md): This quickstart takes you from an initial setup to a functional AI agent.
- [Get Started with Rasa](https://rasa.com/docs/pro/installation/overview.md): Options for getting started with Rasa, including the developer quickstart, MCP tools, Python, and Docker.
- [Using Python](https://rasa.com/docs/pro/installation/python.md): Install Rasa in your local environment.
- [Using Docker](https://rasa.com/docs/pro/installation/docker.md): Run Rasa locally with Docker
- [Licensing](https://rasa.com/docs/pro/installation/licensing.md): License Rasa in your local environment.
- [Rasa MCP Tools](https://rasa.com/docs/pro/installation/rasa-mcp-tools.md): Learn about and configure the Rasa MCP server for Cursor, VS Code, Claude Code, and JetBrains clients.
- [Troubleshooting](https://rasa.com/docs/pro/installation/troubleshooting.md): Troubleshooting issues with your local environment.
- [Configuring Your Assistant](https://rasa.com/docs/pro/build/configuring-assistant.md): Customize how your assistant works through the config.yml, endpoints.yml, and domain.yml files.
- [Writing Flows](https://rasa.com/docs/pro/build/writing-flows.md): How to write flows in Rasa Pro
- [Writing Responses](https://rasa.com/docs/pro/build/writing-responses.md): How to write responses in Rasa
- [Translating Your Assistant](https://rasa.com/docs/pro/build/translating-your-assistant.md): Supporting your users in their preferred language helps create more engaging, accessible, and inclusive assistants.
- [Assistant Memory (Slots)](https://rasa.com/docs/pro/build/assistant-memory.md): How slots provide memory in CALM, storing user data and letting you define, fill, and validate them in the domain and flows.
- [Writing Custom Actions](https://rasa.com/docs/pro/build/custom-actions.md): How to write custom actions that run arbitrary code, and whether to host them on a standalone action server or inside Rasa.
- [Integrating an MCP Server](https://rasa.com/docs/pro/build/mcp-integration.md): Connecting to backend APIs and services via Model Context Protocol (MCP) servers
- [Integrating External Agents via A2A](https://rasa.com/docs/pro/build/integrating-external-agents.md): Connect and orchestrate multiple agents using Agent-to-Agent (A2A) protocol
- [Exposing Rasa as an A2A Sub-Agent](https://rasa.com/docs/pro/build/exposing-rasa-as-a2a-sub-agent.md): Enable your Rasa assistant as a native A2A sub-agent for external orchestrators
- [Configuring Enterprise Search (RAG)](https://rasa.com/docs/pro/build/configuring-enterprise-search.md): Use the Enterprise Search Policy and RAG pipelines to answer informational queries by retrieving documents from a vector store.
- [Voice Assistants](https://rasa.com/docs/pro/build/voice-assistants.md): If you started building your assistant with the Rasa Developer Edition
- [Trying Your Assistant](https://rasa.com/docs/pro/testing/trying-assistant.md): Trying Your Assistant with Inspector
- [Scripted Testing (E2E Testing)](https://rasa.com/docs/pro/testing/evaluating-assistant.md): Evaluating your assistant with E2E Testing
- [Simulating and Evaluating Your Agent](https://rasa.com/docs/pro/testing/simulation-evaluation.md): Use simulation and evaluation to test autonomous CALM agents before shipping — scenario YAMLs drive LLM-simulated conversations that are scored with LLM-as-judge and deterministic assertions.
- [Assistant Tone](https://rasa.com/docs/pro/customize/assistant-tone.md): Customize your assistant's tone
- [Customizing Patterns](https://rasa.com/docs/pro/customize/patterns.md): Customizing conversation patterns
- [Enterprise Search](https://rasa.com/docs/pro/customize/enterprise-search.md): Customize Enterprise Search (RAG)
- [Command Generator](https://rasa.com/docs/pro/customize/command-generator.md): Customize Command Generator
- [Fine-Tuning an LLM for Command Generation](https://rasa.com/docs/pro/customize/fine-tuning-llm.md): How to fine-tune an LLM for Command Generation
- [Quick Deployment with Docker Compose](https://rasa.com/docs/pro/deploy/quick-deploy.md): Use Docker Compose to quickly and cheaply deploy a Rasa CALM Chatbot to a server
- [Deploying to Kubernetes](https://rasa.com/docs/pro/deploy/deploy-kubernetes.md): Deploy Rasa Pro on Kubernetes or OpenShift with the Helm chart, covering secrets, model storage, the action server, and Rasa Pro Services.
- [Setting Up CI/CD](https://rasa.com/docs/pro/deploy/ci-cd.md): Set up a CI/CD pipeline that trains, tests, and deploys a Rasa assistant, with a sample GitHub Actions workflow.
- [LLM Routing](https://rasa.com/docs/pro/deploy/llm-routing.md): Configure Rasa's multi-LLM router to distribute LLM and embedding requests across deployments for load balancing, failover, and cost optimization.
- [Deploying Fine-Tuned LLMs for Command Generation](https://rasa.com/docs/pro/deploy/deploy-fine-tuned-model.md): This page relates to the fine-tuning recipe, which is a beta feature available starting with version 3.10.0
- [Load Testing Guidelines](https://rasa.com/docs/pro/deploy/load-testing.md): Information about how best to scale up your bot to support parallel user activity and how you can use tracing to help debug issues.
- [Analytics](https://rasa.com/docs/pro/improve/analytics.md): How the Analytics Pipeline streams conversation events via Kafka to a data warehouse, with example SQL queries for key metrics.
- [Tracing](https://rasa.com/docs/pro/improve/tracing.md): Enable distributed tracing in Rasa with Jaeger, an OTEL collector, or Langfuse to trace requests, LLM calls, and custom actions.
- [Observability Metrics](https://rasa.com/docs/pro/improve/observability-metrics.md): The custom metrics Rasa emits via OpenTelemetry for LLM usage and performance, and how to enable them alongside tracing.
- [How Does Coexistence Work?](https://rasa.com/docs/pro/calm-with-nlu/coexistence.md): Key Terms
- [Migrating an NLU-based Assistant to CALM](https://rasa.com/docs/pro/calm-with-nlu/migrating-from-nlu.md): The Coexistence feature helps you to migrate from your NLU-based assistant to the
- [Welcome to Studio](https://rasa.com/docs/studio/intro.md): Learn more about Rasa's no code tool for building assistants.
- [Your First Assistant](https://rasa.com/docs/studio/tutorial.md): Rasa Studio Tutorials for CALM assistants
- [Installation Overview](https://rasa.com/docs/studio/installation/overview.md): Overview of the components required for deploying Studio
- [Helm Installation Guide](https://rasa.com/docs/studio/installation/installation-guides/helm-guide.md): Guide for installing Studio with Helm
- [Resource Requirements](https://rasa.com/docs/studio/installation/installation-guides/resource-requirements.md): Resource Requirements for Studio Pods
- [Docker Compose Installation Guide](https://rasa.com/docs/studio/installation/installation-guides/docker-compose-guide.md): Guide for installing Studio with Docker Compose
- [License Activation](https://rasa.com/docs/studio/installation/setup-guides/license-activation.md): Guide on how to active your Rasa Studio license
- [Users and Roles Setup Guide](https://rasa.com/docs/studio/installation/setup-guides/authorization-guide.md): Learn how to set up Studio users with Keycloak and manage their permissions
- [Delete Assistant](https://rasa.com/docs/studio/installation/setup-guides/delete-assistant.md): Learn how to delete a project.
- [How to Set Up Your Assistant](https://rasa.com/docs/studio/build/set-up-your-assistant.md): Create and configure your first Studio assistant.
- [Introduction to Flows](https://rasa.com/docs/studio/build/flow-building/introduction.md): Rasa Studio Flow Introduction
- [How to Create a Flow](https://rasa.com/docs/studio/build/flow-building/create-flows.md): How to create flows with Rasa Studio
- [How to Trigger Flows](https://rasa.com/docs/studio/build/flow-building/trigger-flows.md): Rasa Studio Flow Builder Start
- [How to Send Messages](https://rasa.com/docs/studio/build/flow-building/sending-messages.md): How to write and send messages with Rasa Studio
- [How to Collect Information](https://rasa.com/docs/studio/build/flow-building/collect.md): How your assistant can collect information in Studio.
- [How to Set Slots](https://rasa.com/docs/studio/build/flow-building/set-slots.md): Rasa Studio Flow Builder Set slots
- [How to Make Decisions](https://rasa.com/docs/studio/build/flow-building/logic.md): How to use Logic and Conditions in Studio.
- [How to Link, Call and Connect Flows](https://rasa.com/docs/studio/build/flow-building/linking-flows.md): Learn how to link, call and connect steps in your flows to keep your logic streamlined in Rasa Studio.
- [Flow Builder — Best Practices](https://rasa.com/docs/studio/build/flow-building/best-practices.md): Rasa Studio Flow Builder — Best practices
- [Introduction to Actions](https://rasa.com/docs/studio/build/actions/introduction.md): Learn how to enable your assistant to perform actions in Rasa Studio
- [How to Create a Custom Action](https://rasa.com/docs/studio/build/actions/create-a-custom-action.md): Learn how to enable your assistant to perform actions in Rasa Studio
- [Local Setup for Custom Actions](https://rasa.com/docs/studio/build/actions/local-testing.md): Learn how to test your actions locally in Rasa Studio
- [Managing Content in Studio](https://rasa.com/docs/studio/build/content-management/introduction.md): Learn how to manage content in Rasa Studio
- [Responses](https://rasa.com/docs/studio/build/content-management/responses.md): View, create, edit and remove all your assistant's responses, simple or conditional
- [Translating Your Responses](https://rasa.com/docs/studio/build/content-management/translations.md): Managing translations for your assistant in Studio.
- [Slots](https://rasa.com/docs/studio/build/content-management/slots.md): View, create, edit and remove all your assistant's slots
- [Buttons and Links](https://rasa.com/docs/studio/build/content-management/buttons-and-links.md): View, create, edit and remove all your assistant's buttons and links
- [How to Manage Flows](https://rasa.com/docs/studio/build/content-management/manage-flows.md): Rasa Studio Flow Builder Manage Flows
- [Version Control in Studio](https://rasa.com/docs/studio/build/content-management/version-control.md): Rasa Studio Flow version control
- [How to Use Intents and Entities](https://rasa.com/docs/studio/build/content-management/nlu.md): View, create, edit and remove all your assistant’s intents, entities and examples
- [Conversation Review](https://rasa.com/docs/studio/build/content-management/conversation-review.md): Rasa Studio - Conversation Review for NLU and CALM Assistants
- [Introduction](https://rasa.com/docs/studio/test/introduction.md): Overview of training and testing your assistant in Rasa Studio.
- [Train Your Assistant](https://rasa.com/docs/studio/test/train-your-assistant.md): How to train your assistant in Rasa Studio
- [Try Your Assistant](https://rasa.com/docs/studio/test/try-your-assistant.md): Rasa Studio — Try Your Assistant
- [How to Edit System Flows](https://rasa.com/docs/studio/build/flow-building/system-flows.md): Rasa Studio Flow Builder Start
- [Customize Your Assistant's Prompts](https://rasa.com/docs/studio/customize/custom-prompts.md): How to enable custom prompts in Studio
- [Analytics](https://rasa.com/docs/studio/analyze/analytics.md): Rasa Studio - Monitor and improve your assistant's performance
- [Conversation Review](https://rasa.com/docs/studio/analyze/conversation-review.md): Rasa Studio - Conversation Review for NLU and CALM Assistants
- [How to Annotate Your Conversations](https://rasa.com/docs/studio/analyze/annotation.md): Intent and Entity Annotation guide
- [Authorizing Studio Requests](https://rasa.com/docs/studio/security/authorization.md): How to setup authorization for the Studio API
- [How to Manage Studio Users](https://rasa.com/docs/studio/security/managing-users.md): How to manage user access to Studio
- [Rasa Platform Reference](https://rasa.com/docs/reference/overview.md): Comprehensive technical documentation and reference materials for building with the Rasa platform. Find detailed information about Rasa's components, APIs, configuration options, and technical specifications.
- [Python Versions and Dependencies](https://rasa.com/docs/reference/python-versions-and-dependencies.md): Supported Python versions and dependency groups for Rasa Pro
- [Rasa Primitives](https://rasa.com/docs/reference/primitives.md): All the foundational components used for structuring conversations within Rasa.
- [Business Logic with Flows](https://rasa.com/docs/reference/primitives/flows.md): Flows are part of Rasa's new Conversational AI with Language Models (CALM) approach
- [Flow Steps](https://rasa.com/docs/reference/primitives/flow-steps.md): A flow is made up of one or more steps, each with a specific purpose.
- [Conditions in Flows](https://rasa.com/docs/reference/primitives/conditions.md): Conditions
- [Starting Flows](https://rasa.com/docs/reference/primitives/starting-flows.md): How flows are triggered by LLM command generators or NLU intents, and how NLU triggers and flow guards control when they start.
- [Patterns](https://rasa.com/docs/reference/primitives/patterns.md): Patterns implement Conversation Repair, they're fully customizable and can be used to handle conversations that deviate from the happy path.
- [Responses](https://rasa.com/docs/reference/primitives/responses.md): Defining Responses
- [Contextual Response Rephraser](https://rasa.com/docs/reference/primitives/contextual-response-rephraser.md): The Contextual Response Rephraser is part of Rasa's new
- [Slots](https://rasa.com/docs/reference/primitives/slots.md): Slots are your assistant's memory.
- [Actions](https://rasa.com/docs/reference/primitives/actions.md): Responses
- [Custom Actions](https://rasa.com/docs/reference/primitives/custom-actions.md): In many cases, you can call tools of an MCP (Model Context Protocol) server directly from your flow steps as an alternative to writing custom actions.
- [Default Actions](https://rasa.com/docs/reference/primitives/default-actions.md): Each of these actions have a default behavior, described in the sections below.
- [Events in Rasa](https://rasa.com/docs/reference/primitives/events.md): Conversations are represented as sequences of events: user messages, bot responses, and actions' side effects.
- [Intents and Entities](https://rasa.com/docs/reference/primitives/intents-and-entities.md): Read more about how to format training data with Rasa NLU for open source natural language processing.
- [Training Data Format](https://rasa.com/docs/reference/primitives/training-data-format.md): Description of the YAML format for training data
- [Overview](https://rasa.com/docs/reference/config/overview.md): Configure your Rasa Assistant.
- [Domain](https://rasa.com/docs/reference/config/domain.md): In Rasa, your domain defines the universe in which your assistant operates.
- [Graph Recipe](https://rasa.com/docs/reference/config/components/graph-recipe.md): Learn about Graph Recipe for Rasa.
- [LLM Configuration for Rasa Pro ≥ 3.11](https://rasa.com/docs/reference/config/components/llm-configuration.md): For Rasa Pro versions 3.10 and below, refer to the LLM Configuration for <=3.10 page.
- [LLM Configuration for Rasa Pro ≤ 3.10](https://rasa.com/docs/reference/config/components/llm-configuration-before-3-10.md): For Rasa Pro versions 3.11 and above, refer to the LLM Configuration for >=3.11 page.
- [Overview](https://rasa.com/docs/reference/config/agents/overview-agents.md): Sub Agents are currently in beta and are available starting from Rasa 3.14.0.
- [ReAct Sub Agent](https://rasa.com/docs/reference/config/agents/react-sub-agents.md): ReAct Sub Agents are currently in beta and are available starting from Rasa 3.14.0.
- [External Sub Agent](https://rasa.com/docs/reference/config/agents/external-sub-agents.md): Rasa supports stateful execution of external agents via A2A protocol.
- [LLM Command Generators](https://rasa.com/docs/reference/config/components/llm-command-generators.md): How an LLM-based Command Generator Works
- [NLU Command Adapter](https://rasa.com/docs/reference/config/components/nlu-command-adapter.md): How the NLUCommandAdapter Works
- [Coexistence Routers](https://rasa.com/docs/reference/config/components/coexistence-routers.md): The coexistence of CALM and the NLU-based system depends on a routing
- [Customizing LLM-based Components](https://rasa.com/docs/reference/config/components/llm-custom.md): The LLM components can be extended and modified with custom versions. This
- [NLU Components](https://rasa.com/docs/reference/config/components/nlu-components.md): To use NLU components, you need to install the nlu dependency group:
- [Deprecated Components](https://rasa.com/docs/reference/config/components/deprecated-components.md): SingleStepLLMCommandGenerator
- [Graph-component-interface](https://rasa.com/docs/reference/config/components/example-components/graph-component-interface.md): Graph-component-interface reference documentation for the Rasa Platform.
- [Nlu-component-skeleton](https://rasa.com/docs/reference/config/components/example-components/nlu-component-skeleton.md): Nlu-component-skeleton reference documentation for the Rasa Platform.
- [Registered-component](https://rasa.com/docs/reference/config/components/example-components/registered-component.md): Registered-component reference documentation for the Rasa Platform.
- [Nlu-sparse](https://rasa.com/docs/reference/config/components/example-components/custom-graph-components/nlu-sparse.md): Nlu-sparse reference documentation for the Rasa Platform.
- [Nlu-dense](https://rasa.com/docs/reference/config/components/example-components/custom-graph-components/nlu-dense.md): Nlu-dense reference documentation for the Rasa Platform.
- [Nlu-meta-intent-featurizer](https://rasa.com/docs/reference/config/components/example-components/custom-graph-components/nlu-meta-intent-featurizer.md): Nlu-meta-intent-featurizer reference documentation for the Rasa Platform.
- [Nlu-meta-fallback](https://rasa.com/docs/reference/config/components/example-components/custom-graph-components/nlu-meta-fallback.md): Nlu-meta-fallback reference documentation for the Rasa Platform.
- [Policy Overview](https://rasa.com/docs/reference/config/policies/overview.md): In Rasa, policies are the components responsible for dialogue management.
- [Flow Policy](https://rasa.com/docs/reference/config/policies/flow-policy.md): The Flow Policy is part of Rasa's new
- [Intentless Policy](https://rasa.com/docs/reference/config/policies/intentless-policy.md): The Intentless Policy is deprecated and not recommended for use in Rasa 3.x anymore.
- [Enterprise Search Policy](https://rasa.com/docs/reference/config/policies/enterprise-search-policy.md): The Enterprise Search Policy is part of Rasa's new
- [Generative Search](https://rasa.com/docs/reference/config/policies/generative-search.md): If Generative Search is enabled, the Enterprise Search Policy uses an LLM to generate a relevant, context-aware
- [Extractive Search](https://rasa.com/docs/reference/config/policies/extractive-search.md): Rasa now supports using EnterpriseSearchPolicy without an additional call to LLMs for response generation.
- [Custom Information Retrieval with Enterprise Search Policy](https://rasa.com/docs/reference/config/policies/custom-information-retrievers.md): Rasa now supports Custom Information Retrievers to be used with the EnterpriseSearchPolicy. This feature allows you to integrate your own custom search systems or vector stores with Rasa.
- [Environment Variables](https://rasa.com/docs/reference/config/environment-variables.md): When running Rasa, the RASA_LICENSE environment variable needs to contain
- [PII Management Overview](https://rasa.com/docs/reference/config/pii-management/overview.md): Manage personally identifiable information (PII) collected by your Rasa Assistant.
- [PII Management Prerequisites](https://rasa.com/docs/reference/config/pii-management/prerequisites.md): To use the PII management capability, you need to have the prerequisites in place.
- [Configuring PII Management](https://rasa.com/docs/reference/config/pii-management/configuring-pii-management.md): Learn how to configure PII management in Rasa, including tracker store settings, anonymization rules, and event broker configuration.
- [Session Management Overview](https://rasa.com/docs/reference/config/session-management/overview.md): Manage conversation sessions and user tracking in your Rasa Assistant.
- [User-Scoped Conversations](https://rasa.com/docs/reference/config/session-management/user-scoped-conversations.md): Associate multiple conversations with a single end user using `user_id` in Rasa Pro.
- [Session Lifecycle](https://rasa.com/docs/reference/config/session-management/session-lifecycle.md): Manage conversation sessions in your Rasa Pro Assistant.
- [Session Timer](https://rasa.com/docs/reference/config/session-management/session-timer.md): Configure a session timer to automatically mark conversations as inactive after a period of inactivity.
- [Call Recording](https://rasa.com/docs/reference/config/call-recording.md): Record voice conversations on supported Rasa channels.
- [Studio Environment Variables](https://rasa.com/docs/reference/config/studio-environment-variables.md): Server
- [Test Cases Reference](https://rasa.com/docs/reference/testing/e2e/test-cases.md): This page describe the format for writing test cases.
- [Assertions Reference](https://rasa.com/docs/reference/testing/e2e/assertions.md): This page references all the assertion types you can use in your end-to-end tests to evaluate the behavior of your assistant.
- [Test Coverage](https://rasa.com/docs/reference/testing/e2e/coverage.md): This page describe the format for writing test cases.
- [Test Case Conversion](https://rasa.com/docs/reference/testing/e2e/test-case-conversion.md): End-To-End Test Conversion
- [Dialogue Understanding Tests](https://rasa.com/docs/reference/testing/e2e/dialogue-understanding-tests.md): Dialogue Understanding Tests are currently a beta feature. To enable the feature, set the
- [Simulation and Evaluation](https://rasa.com/docs/reference/testing/evals/overview.md): Validate your agent's behavior with LLM-simulated conversations and deterministic assertions to ensure it meets your goals before shipping.
- [Scenarios](https://rasa.com/docs/reference/testing/evals/scenarios.md): Scenario YAML schema, field reference, assertion types, and sequencing for Rasa simulation and evaluation.
- [Configuration & Results](https://rasa.com/docs/reference/testing/evals/configuration-and-results.md): conftest.yml setup, MCP tool reference, and result file formats for Rasa simulation and evaluation.
- [Connecting to Messaging and Voice Channels](https://rasa.com/docs/reference/channels/messaging-and-voice-channels.md): Check out how to make your Rasa assistant available on platforms like Facebook Messenger, Slack, Telegram or even your very own website.
- [Your Own Website](https://rasa.com/docs/reference/channels/your-own-website.md): Deploy and Run a Rasa Chat Bot on a Website
- [Facebook Messenger](https://rasa.com/docs/reference/channels/facebook-messenger.md): Build a Rasa Chat Bot on Facebook Messenger
- [Slack](https://rasa.com/docs/reference/channels/slack.md): Build a Rasa Chat Bot on Slack
- [Telegram](https://rasa.com/docs/reference/channels/telegram.md): Build a Rasa Chat Bot on Telegram
- [Twilio](https://rasa.com/docs/reference/channels/twilio.md): Deploy a Rasa assistant through text message or WhatsApp via the Twilio connector
- [Google Hangouts Chat](https://rasa.com/docs/reference/channels/hangouts.md): Build a Rasa Chat Bot on Google Hangouts Chat
- [Microsoft Bot Framework](https://rasa.com/docs/reference/channels/microsoft-bot-framework.md): Build a Rasa Chat Bot on Microsoft Bot Framework
- [Cisco Webex Teams](https://rasa.com/docs/reference/channels/cisco-webex-teams.md): Build a Rasa Chat Bot on Cisco Webex
- [RocketChat](https://rasa.com/docs/reference/channels/rocketchat.md): Build a Rasa Chat Bot on Rocketchat
- [Mattermost](https://rasa.com/docs/reference/channels/mattermost.md): Build a Rasa Chat Bot on Mattermost
- [Audiocodes VoiceAI Connect](https://rasa.com/docs/reference/channels/audiocodes-voiceai-connect.md): Build a Rasa Voice Bot on Audiocodes VoiceAI Connect
- [AudioCodes Voice Stream Channel](https://rasa.com/docs/reference/channels/audiocodes-stream.md): From Rasa Pro 3.12, you can stream conversation audio directly from
- [Jambonz as Voice Gateway](https://rasa.com/docs/reference/channels/jambonz.md): Connecting to the Jambonz Voice Gateway
- [Jambonz Voice Stream Channel](https://rasa.com/docs/reference/channels/jambonz-stream.md): From Rasa Pro 3.13, you can stream conversation audio directly from
- [Twilio Voice](https://rasa.com/docs/reference/channels/twilio-voice.md): Deploy a Rasa IVR assistant via the Twilio Voice connector
- [Twilio Media Streams](https://rasa.com/docs/reference/channels/twilio-media-streams.md): Deploy a Rasa IVR assistant via Twilio Media Streams
- [CHIRP](https://rasa.com/docs/reference/channels/chirp.md): Connect a Rasa voice assistant over the CHIRP WebSocket protocol for automated voice testing
- [Genesys Cloud](https://rasa.com/docs/reference/channels/genesys-cloud-voice.md): The Genesys Cloud connector is available from Rasa Pro 3.12
- [SignalWire](https://rasa.com/docs/reference/channels/signalwire.md): Connecting to the SignalWire Voice API
- [Vonage](https://rasa.com/docs/reference/channels/vonage.md): Connecting to the Vonage Voice API
- [WebSocket Voice Channel](https://rasa.com/docs/reference/channels/websockets-voice.md): Stream conversation audio from your own mobile or web app over a plain WebSocket.
- [Custom Connectors](https://rasa.com/docs/reference/channels/custom-connectors.md): Deploy and Run a Rasa Chat Bot on a custom chat interface
- [Model Storage](https://rasa.com/docs/reference/integrations/model-storage.md): You can load your trained model in three different ways:
- [Lock Stores](https://rasa.com/docs/reference/integrations/lock-stores.md): Messages that are being processed lock Rasa for a given conversation ID to ensure that multiple incoming messages for that conversation do not interfere with each other. Rasa provides multiple implementations to maintain conversation locks.
- [Tracker Stores](https://rasa.com/docs/reference/integrations/tracker-stores.md): All conversations are stored within a tracker store. Read how Rasa provides implementations for different store types out of the box.
- [Timer Stores](https://rasa.com/docs/reference/integrations/timer-stores.md): Configure where Rasa Pro stores session timers to ensure they persist across restarts and in multi-pod deployments.
- [Event Brokers](https://rasa.com/docs/reference/integrations/event-brokers.md): Find out how open source chatbot framework Rasa allows you to stream events to a message broker.
- [Secrets Managers](https://rasa.com/docs/reference/integrations/secrets-managers.md): Safeguard credentials your service uses to authenticate to external resources.
- [MCP Servers](https://rasa.com/docs/reference/integrations/mcp-servers.md): Rasa supports native integration of MCP servers.
- [A2A Server](https://rasa.com/docs/reference/integrations/a2a-server.md): Rasa can expose your assistant as a native Agent-to-Agent (A2A) sub-agent.
- [Introduction to Rasa Action Server](https://rasa.com/docs/reference/integrations/action-server/introduction.md): A Rasa action server runs custom actions for a Rasa
- [Actions](https://rasa.com/docs/reference/integrations/action-server/actions.md): When a Rasa assistant calls a custom action, it sends a request to the action server.
- [Events](https://rasa.com/docs/reference/integrations/action-server/events.md): Conversations in Rasa are represented as a sequence of events. Custom actions can
- [Running a Rasa SDK Action Server](https://rasa.com/docs/reference/integrations/action-server/running-action-server.md): Python action server, when built with Python, can be run by using rasa command or directly as a python module.
- [Actions](https://rasa.com/docs/reference/integrations/action-server/sdk-actions.md): The Action class is the base class for any custom action. To
- [Tracker](https://rasa.com/docs/reference/integrations/action-server/sdk-tracker.md): The Tracker class represents a Rasa conversation tracker.
- [Dispatcher](https://rasa.com/docs/reference/integrations/action-server/sdk-dispatcher.md): A dispatcher is an instance of the CollectingDispatcher class used to generate responses to send back to the user.
- [Events](https://rasa.com/docs/reference/integrations/action-server/sdk-events.md): Internally, Rasa conversations are represented as
- [Knowledge Base Actions](https://rasa.com/docs/reference/integrations/action-server/knowledge-bases.md): This feature is experimental.
- [Slot Validation Actions](https://rasa.com/docs/reference/integrations/action-server/validation-action.md): There is a helper class in Rasa SDK with the role of executing custom slot extraction and validation:
- [Deploy Action Server](https://rasa.com/docs/reference/integrations/action-server/deploy-action-server.md): Deploy Action Server on Kubernetes/Openshift using Rasa Pro Helm chart
- [Sanic Extensions](https://rasa.com/docs/reference/integrations/action-server/sanic-extensions.md): You can now extend Sanic features such as middlewares, listeners, background tasks
- [Rasa Action Server gRPC API](https://rasa.com/docs/reference/integrations/action-server/action-server-grpc-api.md): Input and Output
- [Rasa Pro Analytics](https://rasa.com/docs/reference/integrations/analytics.md): Visualize and process Rasa assistant metrics in the tooling of choice.
- [Analytics Database](https://rasa.com/docs/reference/integrations/analytics-database.md): Connect BI tools to the Studio analytics database and understand the underlying data model.
- [Tracing](https://rasa.com/docs/reference/integrations/tracing.md): Trace model training, messages, action-server requests, and streaming voice calls with OpenTelemetry.
- [Langfuse Integration](https://rasa.com/docs/reference/integrations/langfuse.md): Monitor, debug, and improve LLM applications with comprehensive tracing and analytics
- [Natural Language Generation (NLG) Servers](https://rasa.com/docs/reference/integrations/nlg.md): Rasa enables separating response generation by outsourcing responses to an external NLG server, optimizing workflow efficiency.
- [Speech Integrations](https://rasa.com/docs/reference/integrations/speech-integrations.md): Audio Format
- [Kafka-plaintext-endpoint](https://rasa.com/docs/reference/integrations/event-brokers-config/kafka-plaintext-endpoint.md): Kafka-plaintext-endpoint reference documentation for the Rasa Platform.
- [Kafka-sasl-plaintext-endpoint](https://rasa.com/docs/reference/integrations/event-brokers-config/kafka-sasl-plaintext-endpoint.md): Kafka-sasl-plaintext-endpoint reference documentation for the Rasa Platform.
- [Kafka-ssl-endpoint](https://rasa.com/docs/reference/integrations/event-brokers-config/kafka-ssl-endpoint.md): Kafka-ssl-endpoint reference documentation for the Rasa Platform.
- [Kafka-sasl-ssl-endpoint](https://rasa.com/docs/reference/integrations/event-brokers-config/kafka-sasl-ssl-endpoint.md): Kafka-sasl-ssl-endpoint reference documentation for the Rasa Platform.
- [Pika-endpoint](https://rasa.com/docs/reference/integrations/event-brokers-config/pika-endpoint.md): Pika-endpoint reference documentation for the Rasa Platform.
- [Kafka-plaintext-env-vars](https://rasa.com/docs/reference/integrations/analytics-event-broker-config/kafka-plaintext-env-vars.md): Kafka-plaintext-env-vars reference documentation for the Rasa Platform.
- [Kafka-sasl-plaintext-env-vars](https://rasa.com/docs/reference/integrations/analytics-event-broker-config/kafka-sasl-plaintext-env-vars.md): Kafka-sasl-plaintext-env-vars reference documentation for the Rasa Platform.
- [Kafka-ssl-env-vars](https://rasa.com/docs/reference/integrations/analytics-event-broker-config/kafka-ssl-env-vars.md): Kafka-ssl-env-vars reference documentation for the Rasa Platform.
- [Kafka-sasl-ssl-env-vars](https://rasa.com/docs/reference/integrations/analytics-event-broker-config/kafka-sasl-ssl-env-vars.md): Kafka-sasl-ssl-env-vars reference documentation for the Rasa Platform.
- [Rasa Architecture](https://rasa.com/docs/reference/architecture/rasa-pro.md): The diagram below provides an overview of the Rasa Architecture.
- [Rasa as A2A Agent Architecture](https://rasa.com/docs/reference/architecture/rasa-as-a2a-agent.md): When a2a_server is configured in endpoints.yml, Rasa registers A2A JSON-RPC routes on the same Sanic port as REST and channel webhooks.
- [Studio Architecture](https://rasa.com/docs/reference/architecture/studio.md): Rasa Studio architecture
- [Multi-LLM Routing](https://rasa.com/docs/reference/deployment/multi-llm-routing.md): The Multi-LLM-Routing is available starting with version 3.11.0.
- [Studio Infrastructure Requirements](https://rasa.com/docs/reference/deployment/studio-hardware-requirements.md): Minimum Hardware Requirements
- [Rasa Pro Infrastructure Requirements](https://rasa.com/docs/reference/deployment/pro-hardware-requirements.md): Minimum Hardware Requirements
- [Automatic Conversation Deletion in Studio](https://rasa.com/docs/reference/deployment/automatic-conversation-deletion.md): The Automatic Conversation Deletion allows for the periodic removal of old conversations and their associated data from Studio.
- [Deploying Fine-Tuned LLMs for Command Generation](https://rasa.com/docs/reference/deployment/deploy-fine-tuned-model.md): This page provides detailed steps for different options and optimizations of hosting a fine-tuned LLM.
- [Rasa Pro Port and Protocol Rules](https://rasa.com/docs/reference/deployment/pro-port-and-protocol-rules.md): A Rasa Pro deployment consists of various components that need to communicate with each other.
- [Analytics Pipeline: Data Structure Reference](https://rasa.com/docs/reference/api/analytics-data-structure-reference.md): The data structure is created by the Analytics pipeline and treated as
- [Command Line Interface](https://rasa.com/docs/reference/api/command-line-interface.md): Command line interface for Rasa. Learn how to train, test and run your machine learning-based conversational AI assistants
- [Rasa MCP Tools API Reference](https://rasa.com/docs/reference/api/rasa-mcp-tools.md): Reference for the Rasa MCP tools available through the local Rasa MCP server.
- [Enabling the Rasa REST API](https://rasa.com/docs/reference/api/pro/rasa-pro-rest-api.md): Read about Rasa's REST API that has endpoints for conversations, training models, and configuring your bot.
- [Health endpoint of Rasa Server](https://rasa.com/docs/reference/api/pro/http-api/server-information/health-endpoint-of-rasa-server.md): This URL can be used as an endpoint to run health checks against. When the server is running this will return 200.
- [Information about your Rasa Pro License](https://rasa.com/docs/reference/api/pro/http-api/server-information/information-about-your-rasa-pro-license.md): Returns the license information about your Rasa Pro License
- [Version of Rasa](https://rasa.com/docs/reference/api/pro/http-api/server-information/version-of-rasa.md): Returns the version of Rasa.
- [Status of the Rasa server](https://rasa.com/docs/reference/api/pro/http-api/server-information/status-of-the-rasa-server.md): Information about the server and the currently loaded Rasa model.
- [Retrieve a conversations tracker](https://rasa.com/docs/reference/api/pro/http-api/tracker/retrieve-a-conversations-tracker.md): The tracker represents the state of the conversation. The state of the tracker is created by applying a sequence of events, which modify the state. These events can optionally be included in the response.
- [Delete tracker for a specific conversation](https://rasa.com/docs/reference/api/pro/http-api/tracker/delete-tracker-for-a-specific-conversation.md): Deletes the tracker of a conversation.
- [Retrieve all conversations for a user](https://rasa.com/docs/reference/api/pro/http-api/tracker/retrieve-all-conversations-for-a-user.md): Retrieves all conversation trackers for a given user with pagination. All the event data is returned. Requires admin authentication (token or JWT with `role` set to `admin`).
- [Replace a trackers events](https://rasa.com/docs/reference/api/pro/http-api/tracker/replace-a-trackers-events.md): Replaces all events of a tracker with the passed list of events. This endpoint should not be used to modify trackers in a production setup, but rather for creating training data.
- [Append events to a tracker](https://rasa.com/docs/reference/api/pro/http-api/tracker/append-events-to-a-tracker.md): Appends one or multiple new events to the tracker state of the conversation. Any existing events will be kept and the new events will be appended, updating the existing state. If events are appended to a new conversation ID, the tracker will be initialised with a new session.
- [Retrieve an end-to-end story corresponding to a conversation](https://rasa.com/docs/reference/api/pro/http-api/tracker/retrieve-an-end-to-end-story-corresponding-to-a-conversation.md): The story represents the whole conversation in end-to-end format. This can be posted to the '/test/stories' endpoint and used as a test.
- [Run an action in a conversation](https://rasa.com/docs/reference/api/pro/http-api/tracker/run-an-action-in-a-conversation.md): DEPRECATED. Runs the action, calling the action server if necessary. Any responses sent by the executed action will be forwarded to the channel specified in the output_channel parameter. If no output channel is specified, any messages that should be sent to the user will be included in the response…
- [Inject an intent into a conversation](https://rasa.com/docs/reference/api/pro/http-api/tracker/inject-an-intent-into-a-conversation.md): Sends a specified intent and list of entities in place of a user message. The bot then predicts and executes a response action. Any responses sent by the executed action will be forwarded to the channel specified in the ``output_channel`` parameter. If no output channel is specified, any messages th…
- [Predict the next action](https://rasa.com/docs/reference/api/pro/http-api/tracker/predict-the-next-action.md): Runs the conversations tracker through the model's policies to predict the scores of all actions present in the model's domain. Actions are returned in the 'scores' array, sorted on their 'score' values. The state of the tracker is not modified.
- [Add a message to a tracker](https://rasa.com/docs/reference/api/pro/http-api/tracker/add-a-message-to-a-tracker.md): Adds a message to a tracker. This doesn't trigger the prediction loop. It will log the message on the tracker and return, no actions will be predicted or run. This is often used together with the predict endpoint.
- [Retrieve capabilities for a conversation](https://rasa.com/docs/reference/api/pro/http-api/tracker/retrieve-capabilities-for-a-conversation.md): Returns structured, conversation-aware capabilities metadata for all flows, including whether each flow is currently startable based on guard evaluation for the given conversation state. This endpoint is intended for use by custom actions and external integrations to build dynamic "what can you do?"…
- [Train a Rasa model](https://rasa.com/docs/reference/api/pro/http-api/model/train-a-rasa-model.md): Trains a new Rasa model. Depending on the data given only a dialogue model, only a NLU model, or a model combining a trained dialogue model with an NLU model will be trained. The new model is not loaded by default.
- [Evaluate stories](https://rasa.com/docs/reference/api/pro/http-api/model/evaluate-stories.md): Evaluates one or multiple stories against the currently loaded Rasa model.
- [Perform an intent evaluation](https://rasa.com/docs/reference/api/pro/http-api/model/perform-an-intent-evaluation.md): Evaluates NLU model against a model or using cross-validation.
- [Predict an action on a temporary state](https://rasa.com/docs/reference/api/pro/http-api/model/predict-an-action-on-a-temporary-state.md): Predicts the next action on the tracker state as it is posted to this endpoint. Rasa will create a temporary tracker from the provided events and will use it to predict an action. No messages will be sent and no action will be run.
- [Parse a message using the Rasa model](https://rasa.com/docs/reference/api/pro/http-api/model/parse-a-message-using-the-rasa-model.md): Predicts the intent and entities of the message posted to this endpoint. No messages will be stored to a conversation and no action will be run. This will just retrieve the NLU parse results.
- [Replace the currently loaded model](https://rasa.com/docs/reference/api/pro/http-api/model/replace-the-currently-loaded-model.md): Updates the currently loaded model. First, tries to load the model from the local (note: local to Rasa server) storage system. Secondly, tries to load the model from the provided model server configuration. Last, tries to load the model from the provided remote storage.
- [Unload the trained model](https://rasa.com/docs/reference/api/pro/http-api/model/unload-the-trained-model.md): Unloads the currently loaded trained model from the server.
- [Retrieve the flows of the assistant](https://rasa.com/docs/reference/api/pro/http-api/flows/retrieve-the-flows-of-the-assistant.md): Returns the assistant was trained on.
- [Retrieve the loaded domain](https://rasa.com/docs/reference/api/pro/http-api/domain/retrieve-the-loaded-domain.md): Returns the domain specification the currently loaded model is using.
- [Post user message from a REST channel](https://rasa.com/docs/reference/api/pro/http-api/channel-webhooks/post-user-message-from-a-rest-channel.md): Post a message from the user and forward it to the assistant. Return the message of the assistant to the user.
- [Post user message from a custom channel](https://rasa.com/docs/reference/api/pro/http-api/channel-webhooks/post-user-message-from-a-custom-channel.md): Post a message from the user and forward it to the assistant. Return the message of the assistant to the user. This is from a custom channel.
- [Core request to execute a custom action](https://rasa.com/docs/reference/api/pro/action-server-api/core-request-to-execute-a-custom-action.md): Rasa Core sends a request to the action server to execute a certain custom action. As a response to the action call from Core, you can modify the tracker, e.g. by setting slots and send responses back to the user.
- [Authorization](https://rasa.com/docs/reference/api/studio/api-authorization.md): Authorization for Studio API
- [Conversation API](https://rasa.com/docs/reference/api/studio/conversation-api.md): GraphQL API for retrieving, deleting, and tagging conversations in Rasa Studio.
- [Model Download API for CI Integration](https://rasa.com/docs/reference/api/studio/ci-integration-api.md): GraphQL API for retrieving download URLs for trained models and input data from Rasa Studio for CI/CD integration.
- [Rasa Telemetry](https://rasa.com/docs/reference/telemetry.md): Rasa utilizes telemetry to gather usage data, helping us continuously improve Rasa
- [Telemetry Event Reference](https://rasa.com/docs/reference/telemetry/events.md): Telemetry events are only reported if telemetry is enabled. A detailed explanation
- [Compatibility Matrix for the Rasa Platform](https://rasa.com/docs/reference/changelogs/compatibility-matrix.md): Information about compatibility between Rasa Studio, Rasa Pro and Rasa Pro Services.
- [Rasa Pro Change Log](https://rasa.com/docs/reference/changelogs/rasa-pro-changelog.md): All notable changes to Rasa Pro will be documented in this page.
- [Rasa Pro Version Migration Guide](https://rasa.com/docs/reference/changelogs/rasa-pro-migration-guide.md): Information about changes between major versions of chatbot framework Rasa and how you can migrate from one version to another.
- [Studio Change Log](https://rasa.com/docs/reference/changelogs/studio-changelog.md): Release changelog and version history for Rasa Studio.
- [Studio Version Migration Guide](https://rasa.com/docs/reference/changelogs/studio-version-migration-guide.md): Information about changes between major versions of Rasa Studio and how you can migrate from one version to another.
- [Rasa Pro Services Change Log](https://rasa.com/docs/reference/changelogs/rasa-pro-services-changelog.md): All notable changes to Rasa Pro Services will be documented in this page.
- [Rasa SDK Change Log](https://rasa.com/docs/reference/changelogs/rasa-sdk-changelog.md): The Rasa SDK changelog can be found in the Rasa SDK repository

## OpenAPI Specs

- [action-server](/docs/openapi/action-server.yaml)
- [pro](/docs/openapi/pro.yaml)


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.