# Galtea Docs

- [Introduction](https://docs.galtea.ai/introduction.md): Evaluate, test, and monitor your AI products with Galtea.
- [Registration](https://docs.galtea.ai/registration.md): Create your Galtea account and sign in
- [Quickstart](https://docs.galtea.ai/quickstart.md): Validate your AI product with Galtea
- [Writing Effective Specifications](https://docs.galtea.ai/sdk/tutorials/writing-specifications.md): Learn how to write clear specification descriptions that power AI-generated datasets and metrics.
- [Specification-Driven Evaluations](https://docs.galtea.ai/sdk/tutorials/specification-driven-evaluations.md): Define what your product should do, generate metrics from specs, and create datasets — all driven by specifications
- [Simulating User Conversations](https://docs.galtea.ai/sdk/tutorials/simulating-conversations.md): Learn how to use Galtea's Conversation Simulator to test your AI with simulated multi-turn conversations.
- [Evaluating Conversations](https://docs.galtea.ai/sdk/tutorials/evaluating-conversations.md): Learn how to evaluate multi-turn conversations using Galtea's session-based workflow across dataset-based, past conversations, and production monitoring.
- [Create a Custom Dataset](https://docs.galtea.ai/sdk/tutorials/create-dataset.md): Learn how to create and upload custom datasets using the SDK
- [Run Dataset-Based Evaluations](https://docs.galtea.ai/sdk/tutorials/run-dataset-based-evaluations.md): Learn how to run evaluations for a single-turn, dataset-based workflow.
- [Direct Inferences and Evaluations from the Platform](https://docs.galtea.ai/sdk/tutorials/direct-inferences-and-evaluations-from-platform.md): Learn how to configure Endpoint Connections to run inferences and evaluations directly from the Galtea Dashboard, without writing any SDK code.
- [Monitor Production Responses](https://docs.galtea.ai/sdk/tutorials/monitor-production-responses-to-user-queries.md): Learn how to log and evaluate user queries from your production environment.
- [Send OpenTelemetry Traces to Galtea](https://docs.galtea.ai/sdk/tutorials/send-opentelemetry-traces-to-galtea.md): Configure an OpenTelemetry exporter or Collector to reach Galtea's public OTel endpoint: endpoint, authentication, and how spans map to Span records.
- [Monitor Real User Traffic via OpenTelemetry](https://docs.galtea.ai/sdk/tutorials/monitor-real-user-traffic-with-opentelemetry.md): Send your live traffic's OpenTelemetry traces to Galtea to create production sessions that Monitors evaluate automatically.
- [How to create your judge prompt?](https://docs.galtea.ai/sdk/tutorials/how-to-create-your-llm-as-a-judge-prompt.md): A practical guide for writing LLM-as-a-judge prompts: define objective evaluation criteria, unambiguous scoring rubrics, and machine-friendly outputs.
- [Evaluate with Custom Metrics](https://docs.galtea.ai/sdk/tutorials/evaluate-with-custom-metrics.md): Learn how to run evaluations with your own custom, self-hosted metrics.
- [Tracing Agent Operations](https://docs.galtea.ai/sdk/tutorials/tracing-agent-operations.md): Learn how to capture and analyze the internal operations of your AI agent
- [How to evaluate your agentic system?](https://docs.galtea.ai/sdk/tutorials/how-to-evaluate-your-agentic-system.md): A practical guide for evaluating your agentic system: use Galtea's tracing feature to capture your agent's spans and then define your specific scope of interest by creating a custom metric.
- [Human Evaluation](https://docs.galtea.ai/sdk/tutorials/human-evaluation.md): Set up user groups, create human evaluation metrics, and let your team manually review and score AI outputs
- [Improve Your Product with Evaluations and an AI Agent](https://docs.galtea.ai/playbooks/improve-product-with-ai-agent.md): Use the Galtea Agent Skill and CLI to find what your LLM product is getting wrong, fix it, and prove the fix — without leaving your editor.
- [Agent Skill](https://docs.galtea.ai/sdk/integrations/agent-skill.md): Install the Galtea Agent Skill so Claude Code, Cursor, and other AI coding assistants can drive Galtea on your behalf.
- [Langfuse Integration](https://docs.galtea.ai/sdk/integrations/langfuse/overview.md): Send your Langfuse traces to Galtea for evaluation — swap one import, zero extra config
- [Langfuse Integration](https://docs.galtea.ai/sdk/api/langfuse/service.md): Langfuse integration API reference for the Galtea SDK
- [observe](https://docs.galtea.ai/sdk/api/langfuse/observe.md): Drop-in replacement for Langfuse's @observe decorator with Galtea span linking.
- [start_as_current_observation](https://docs.galtea.ai/sdk/api/langfuse/start-as-current-observation.md): Drop-in replacement for Langfuse's start_as_current_observation context manager with Galtea span linking.
- [CallbackHandler](https://docs.galtea.ai/sdk/api/langfuse/callback-handler.md): Drop-in replacement for Langfuse's langchain.CallbackHandler with Galtea span linking.
- [Langfuse Integration Guide](https://docs.galtea.ai/sdk/integrations/langfuse/integration-guide.md): What changes when you add Galtea evaluation to your Langfuse-instrumented app
- [GitHub Actions](https://docs.galtea.ai/sdk/integrations/github-actions.md): Learn how to integrate Galtea's evaluation capabilities into your GitHub Actions workflow
- [Roles & Permissions](https://docs.galtea.ai/security/roles-and-permissions.md): What each organization role can do on the Galtea platform
- [SAML SSO](https://docs.galtea.ai/security/saml-sso.md): Allow your team to sign in to Galtea through your company's identity provider using SAML 2.0 single sign-on
- [Microsoft Entra ID (Azure AD)](https://docs.galtea.ai/security/saml-sso/azure.md): Step-by-step guide to configure SAML SSO with Microsoft Entra ID (formerly Azure Active Directory)
- [Okta](https://docs.galtea.ai/security/saml-sso/okta.md): Step-by-step guide to configure SAML SSO with Okta
- [Google Workspace](https://docs.galtea.ai/security/saml-sso/google.md): Step-by-step guide to configure SAML SSO with Google Workspace
- [Dataset, Trace, and Span Renames](https://docs.galtea.ai/sdk/migration-guides/entity-renames.md): How to update your SDK and CLI code for the new entity names in version 5.0.0
- [Overview](https://docs.galtea.ai/concepts/overview.md): How Galtea's concepts connect
- [Installation](https://docs.galtea.ai/sdk/installation.md): Learn how to install the SDK and set up your environment
- [Usage](https://docs.galtea.ai/sdk/usage.md): Learn how to use the SDK in your codebases
- [Galtea Client](https://docs.galtea.ai/sdk/api/galtea.md): Main entry point for the Galtea SDK
- [Installation](https://docs.galtea.ai/cli/installation.md): Install the Galtea CLI on your platform
- [Usage](https://docs.galtea.ai/cli/usage.md): Authenticate the Galtea CLI and explore the command surface
- [Product](https://docs.galtea.ai/concepts/product.md): A functionality or service evaluated by Galtea
- [Product Service](https://docs.galtea.ai/sdk/api/product/service.md): Product Service API methods in the Galtea SDK
- [Listing Products](https://docs.galtea.ai/sdk/api/product/list.md): This method allows you to list many products.
- [Retrieving Product](https://docs.galtea.ai/sdk/api/product/get.md): Retrieve a specific product by its ID.
- [Retrieving Product By Name](https://docs.galtea.ai/sdk/api/product/get-by-name.md): Retrieve a specific product by its name.
- [Deleting Product](https://docs.galtea.ai/sdk/api/product/delete.md): Delete a specific product by its ID.
- [Specification](https://docs.galtea.ai/concepts/product/specification.md): A testable behavioral expectation for a product
- [Specifications Service](https://docs.galtea.ai/sdk/api/specification/service.md): Specifications Service API methods in the Galtea SDK
- [Create Specification](https://docs.galtea.ai/sdk/api/specification/create.md): Create a specification for a product.
- [Listing Specifications](https://docs.galtea.ai/sdk/api/specification/list.md): List specifications with optional filters.
- [Retrieving Specification](https://docs.galtea.ai/sdk/api/specification/get.md): Retrieve a specific specification by its ID.
- [Deleting Specification](https://docs.galtea.ai/sdk/api/specification/delete.md): Delete a specific specification by its ID.
- [Link Metrics](https://docs.galtea.ai/sdk/api/specification/link-metrics.md): Link metrics to a specification.
- [Unlink Metrics](https://docs.galtea.ai/sdk/api/specification/unlink-metrics.md): Unlink metrics from a specification.
- [Get Linked Metrics](https://docs.galtea.ai/sdk/api/specification/get-metrics.md): Get all metrics linked to a specification.
- [Link Datasets](https://docs.galtea.ai/sdk/api/specification/link-datasets.md): Link datasets to a specification.
- [Unlink Datasets](https://docs.galtea.ai/sdk/api/specification/unlink-datasets.md): Unlink datasets from a specification.
- [Get Linked Datasets](https://docs.galtea.ai/sdk/api/specification/get-datasets.md): Get all datasets linked to a specification.
- [Monitor](https://docs.galtea.ai/concepts/product/monitor.md): An always-on evaluation rule for production sessions
- [Monitors Service](https://docs.galtea.ai/sdk/api/monitor/service.md): Monitors Service API methods in the Galtea SDK
- [Create Monitor](https://docs.galtea.ai/sdk/api/monitor/create.md): Create a monitor for a product.
- [Listing Monitors](https://docs.galtea.ai/sdk/api/monitor/list.md): List monitors with optional filters.
- [Retrieving Monitor](https://docs.galtea.ai/sdk/api/monitor/get.md): Retrieve a specific monitor by its ID.
- [Updating Monitor](https://docs.galtea.ai/sdk/api/monitor/update.md): Update an existing monitor, including pausing and resuming it.
- [Deleting Monitor](https://docs.galtea.ai/sdk/api/monitor/delete.md): Delete a specific monitor by its ID.
- [Version](https://docs.galtea.ai/concepts/product/version.md): A specific iteration of a product in Galtea
- [Version Service](https://docs.galtea.ai/sdk/api/version/service.md): Version Service API methods in the Galtea SDK
- [Create Version](https://docs.galtea.ai/sdk/api/version/create.md): Create a version for your product.
- [Listing Versions](https://docs.galtea.ai/sdk/api/version/list.md): List all versions associated with a specific product.
- [Retrieving Version](https://docs.galtea.ai/sdk/api/version/get.md): Retrieve a specific version by its ID.
- [Retrieving Version By Name](https://docs.galtea.ai/sdk/api/version/get-by-name.md): Retrieve a specific version by its name.
- [Deleting Version](https://docs.galtea.ai/sdk/api/version/delete.md): Delete a specific version by its ID.
- [Endpoint Connection](https://docs.galtea.ai/concepts/product/endpoint-connection.md): A reusable connection to an external endpoint that defines how to connect to your AI system's API.
- [Input Schema](https://docs.galtea.ai/concepts/product/endpoint-connection-input-schema.md): Define the structure of test case inputs so Galtea can generate structured, multi-field test data for your endpoint.
- [Templates & Mapping](https://docs.galtea.ai/concepts/product/endpoint-connection-configuration.md): Configure how Galtea formats requests to your endpoint, extracts values from responses, sets custom headers, and handles retries.
- [Structured Input Template Syntax](https://docs.galtea.ai/concepts/product/endpoint-connection-template-syntax.md): Reference for the {{ input.field_name }}, {{ context.field_name }}, {{ language_code }}, and {{ language_name }} template syntax used in endpoint connection input templates.
- [Endpoint Connection Service](https://docs.galtea.ai/sdk/api/endpoint-connection/service.md): Endpoint Connection Service API methods in the Galtea SDK
- [Create Endpoint Connection](https://docs.galtea.ai/sdk/api/endpoint-connection/create.md): Create a new endpoint connection for a product.
- [List Endpoint Connections](https://docs.galtea.ai/sdk/api/endpoint-connection/list.md): List endpoint connections with optional filters.
- [Get Endpoint Connection](https://docs.galtea.ai/sdk/api/endpoint-connection/get.md): Retrieve a specific endpoint connection by its ID.
- [Get Endpoint Connection By Name](https://docs.galtea.ai/sdk/api/endpoint-connection/get-by-name.md): Retrieve a specific endpoint connection by its name within a product.
- [Update Endpoint Connection](https://docs.galtea.ai/sdk/api/endpoint-connection/update.md): Update an existing endpoint connection.
- [Delete Endpoint Connection](https://docs.galtea.ai/sdk/api/endpoint-connection/delete.md): Delete a specific endpoint connection by its ID.
- [Test Connection](https://docs.galtea.ai/sdk/api/endpoint-connection/test-connection.md): Test an endpoint connection by making a sample request.
- [Phone Connection](https://docs.galtea.ai/concepts/product/phone-connection.md): A reusable telephony connection that lets Galtea dial your AI agent's phone number for voice evaluation.
- [Phone Connection Service](https://docs.galtea.ai/sdk/api/phone-connection/service.md): Phone Connection Service API methods in the Galtea SDK
- [Create Phone Connection](https://docs.galtea.ai/sdk/api/phone-connection/create.md): Create a new phone connection for a product.
- [List Phone Connections](https://docs.galtea.ai/sdk/api/phone-connection/list.md): List phone connections with optional filters.
- [Get Phone Connection](https://docs.galtea.ai/sdk/api/phone-connection/get.md): Retrieve a specific phone connection by its ID.
- [Get Phone Connection By Name](https://docs.galtea.ai/sdk/api/phone-connection/get-by-name.md): Retrieve a specific phone connection by its name within a product.
- [Update Phone Connection](https://docs.galtea.ai/sdk/api/phone-connection/update.md): Update an existing phone connection.
- [Delete Phone Connection](https://docs.galtea.ai/sdk/api/phone-connection/delete.md): Delete a specific phone connection by its ID.
- [WebRTC Connection](https://docs.galtea.ai/concepts/product/webrtc-connection.md): A reusable connection that lets Galtea reach your AI voice agent over WebRTC for voice evaluation.
- [WebRTC Connection Service](https://docs.galtea.ai/sdk/api/webrtc-connection/service.md): WebRTC Connection Service API methods in the Galtea SDK
- [Create WebRTC Connection](https://docs.galtea.ai/sdk/api/webrtc-connection/create.md): Create a new WebRTC connection for a product.
- [List WebRTC Connections](https://docs.galtea.ai/sdk/api/webrtc-connection/list.md): List WebRTC connections with optional filters.
- [Get WebRTC Connection](https://docs.galtea.ai/sdk/api/webrtc-connection/get.md): Retrieve a specific WebRTC connection by its ID.
- [Get WebRTC Connection By Name](https://docs.galtea.ai/sdk/api/webrtc-connection/get-by-name.md): Retrieve a specific WebRTC connection by its name within a product.
- [Update WebRTC Connection](https://docs.galtea.ai/sdk/api/webrtc-connection/update.md): Update an existing WebRTC connection.
- [Delete WebRTC Connection](https://docs.galtea.ai/sdk/api/webrtc-connection/delete.md): Delete a specific WebRTC connection by its ID.
- [Dataset](https://docs.galtea.ai/concepts/product/dataset.md): A dataset of test cases for evaluating product performance
- [Data Augmentation](https://docs.galtea.ai/concepts/product/dataset/data-augmentation.md): Automatically expand your datasets from a handful of examples into comprehensive, realistic datasets
- [Extend Test Cases](https://docs.galtea.ai/concepts/product/dataset/extend-test-cases.md): Add more test cases to a Galtea-generated dataset by re-running the generator that created it
- [Accuracy Datasets](https://docs.galtea.ai/concepts/product/dataset/accuracy-datasets.md): Evaluate the accuracy and correctness of your outputs
- [Security & Safety Datasets](https://docs.galtea.ai/concepts/product/dataset/security-datasets.md): Evaluate security, safety, and bias aspects of your AI products
- [Threats](https://docs.galtea.ai/concepts/product/dataset/security-threats.md): Galtea platform tests the robustness of your product against multiple types of threats
- [Strategies](https://docs.galtea.ai/concepts/product/dataset/security-strategies.md): Galtea platform uses a variety of security strategies to generate adversarial test cases and evaluate the robustness of your product.
- [Behavior Datasets](https://docs.galtea.ai/concepts/product/dataset/behavior-datasets.md): Evaluate multi-turn dialogue interactions using conversation simulation with simulated users
- [Dataset Service](https://docs.galtea.ai/sdk/api/dataset/service.md): Dataset Service API methods in the Galtea SDK
- [Create Dataset](https://docs.galtea.ai/sdk/api/dataset/create.md): Create a dataset for your product.
- [Listing Datasets](https://docs.galtea.ai/sdk/api/dataset/list.md): List all datasets associated with a specific product.
- [Retrieving Dataset](https://docs.galtea.ai/sdk/api/dataset/get.md): Retrieve a specific dataset by its ID.
- [Retrieving Dataset By Name](https://docs.galtea.ai/sdk/api/dataset/get-by-name.md): Retrieve a specific dataset by its name.
- [Update Dataset](https://docs.galtea.ai/sdk/api/dataset/update.md): Update the name or metadata of an existing dataset
- [Deleting Dataset](https://docs.galtea.ai/sdk/api/dataset/delete.md): Delete a specific dataset by its ID.
- [Downloading Dataset](https://docs.galtea.ai/sdk/api/dataset/download.md): Download the file associated with a specific dataset.
- [Test Case](https://docs.galtea.ai/concepts/product/dataset/test-case.md): A single challenge for evaluating product performance
- [Test Case Service](https://docs.galtea.ai/sdk/api/test-case/service.md): Test Case Service API methods in the Galtea SDK
- [Create Test Case](https://docs.galtea.ai/sdk/api/test-case/create.md): Create a test case for your dataset.
- [Listing Test Cases](https://docs.galtea.ai/sdk/api/test-case/list.md): List all test cases associated with a specific dataset.
- [Retrieving Test Case](https://docs.galtea.ai/sdk/api/test-case/get.md): Retrieve a specific test case by its ID.
- [Deleting Test Case](https://docs.galtea.ai/sdk/api/test-case/delete.md): Delete a specific test case by its ID.
- [Conversation Simulator](https://docs.galtea.ai/concepts/product/dataset/test-case/conversation-simulator.md): Test your conversational AI by simulating realistic multi-turn user interactions.
- [Simulator Service](https://docs.galtea.ai/sdk/api/simulator/service.md): Simulator Service API methods in the Galtea SDK for running multi-turn conversation simulations.
- [Simulate Conversation](https://docs.galtea.ai/sdk/api/simulator/simulate.md): Run a full conversation simulation between your agent and a simulated user using the Galtea SDK.
- [AgentInput](https://docs.galtea.ai/sdk/api/agent/input.md): Reference for the AgentInput object received by structured agent functions and Agent.call()
- [Session](https://docs.galtea.ai/concepts/product/version/session.md): A group of traces that make up a full conversation
- [Session Service](https://docs.galtea.ai/sdk/api/session/service.md): Session Service API methods in the Galtea SDK
- [Create Session](https://docs.galtea.ai/sdk/api/session/create.md): Create a new session to group traces.
- [Get Or Create Session](https://docs.galtea.ai/sdk/api/session/get-or-create.md): Get an existing session or create a new one if it doesn't exist.
- [List Sessions](https://docs.galtea.ai/sdk/api/session/list.md): List sessions with optional filtering.
- [Get Session](https://docs.galtea.ai/sdk/api/session/get.md): Retrieve a specific session by its ID.
- [Get Session By Custom ID](https://docs.galtea.ai/sdk/api/session/get-by-custom-id.md): Retrieve a specific session by its Custom ID.
- [Delete Session](https://docs.galtea.ai/sdk/api/session/delete.md): Delete a specific session and all its associated data.
- [Update Session](https://docs.galtea.ai/sdk/api/session/update.md): Update an existing session with metadata and status information
- [Finish Session](https://docs.galtea.ai/sdk/api/session/finish.md): Mark a session as finished (closed) so it becomes eligible for evaluation
- [Trace](https://docs.galtea.ai/concepts/product/version/session/trace.md): A single turn in a conversation between a user and an AI system
- [Trace Service](https://docs.galtea.ai/sdk/api/trace/service.md): Trace Service API methods in the Galtea SDK
- [Generate Trace](https://docs.galtea.ai/sdk/api/trace/generate.md): Execute an agent and automatically capture spans, latency, and metadata
- [Create Trace](https://docs.galtea.ai/sdk/api/trace/create.md): Create a new trace log in a session.
- [Create and Evaluate Trace](https://docs.galtea.ai/sdk/api/trace/create-and-evaluate.md): Create a trace and immediately evaluate it against specified metrics in a single call.
- [Create Trace Batch](https://docs.galtea.ai/sdk/api/trace/create-batch.md): Create a batch of traces in a session.
- [Update Trace](https://docs.galtea.ai/sdk/api/trace/update.md): Update an existing trace with agent output and metadata
- [List Traces](https://docs.galtea.ai/sdk/api/trace/list.md): List trace logs for a session.
- [Get Trace](https://docs.galtea.ai/sdk/api/trace/get.md): Retrieve a trace log by its ID.
- [Delete Trace](https://docs.galtea.ai/sdk/api/trace/delete.md): Delete a trace log by its ID.
- [Span](https://docs.galtea.ai/concepts/product/version/session/span.md): Track and visualize the internal operations of your AI agent during inference
- [Span Service](https://docs.galtea.ai/sdk/api/span/service.md): Span Service API methods in the Galtea SDK
- [start_span](https://docs.galtea.ai/sdk/api/span/start-span.md): Context manager for creating spans with fine-grained control.
- [Set Context](https://docs.galtea.ai/sdk/api/span/set-context.md): Set Galtea context values for span correlation.
- [Clear Context](https://docs.galtea.ai/sdk/api/span/clear-context.md): Clear a previously attached context and optionally flush pending spans.
- [Create Span](https://docs.galtea.ai/sdk/api/span/create.md): Create a single span directly via the API.
- [Create Span Batch](https://docs.galtea.ai/sdk/api/span/create-batch.md): Create multiple spans in a single API call.
- [List Spans](https://docs.galtea.ai/sdk/api/span/list.md): Retrieve spans for a trace.
- [Get Span](https://docs.galtea.ai/sdk/api/span/get.md): Retrieve a single span by ID.
- [Delete Span](https://docs.galtea.ai/sdk/api/span/delete.md): Delete a span by ID.
- [@traced Decorator](https://docs.galtea.ai/sdk/api/span/traced-decorator.md): Automatically trace function calls with OpenTelemetry.
- [Metric](https://docs.galtea.ai/concepts/metric.md): Criteria and methods for evaluating AI product performance
- [Evaluation Types](https://docs.galtea.ai/concepts/metric/evaluation-types.md): How metrics are scored: Self-Hosted, AI Evaluation, or Human Evaluation
- [Evaluation Parameters](https://docs.galtea.ai/concepts/metric/evaluation-parameters.md): Data fields available to metric evaluators during scoring
- [AI Metric Generation](https://docs.galtea.ai/concepts/metric/ai-generation.md): Automatically generate evaluation metrics from your product specifications using AI
- [Metrics Service](https://docs.galtea.ai/sdk/api/metric/service.md): Metrics Service API methods in the Galtea SDK
- [Create Metric](https://docs.galtea.ai/sdk/api/metric/create.md): Create a metric for evaluating your products.
- [Listing Metrics](https://docs.galtea.ai/sdk/api/metric/list.md): List all metrics.
- [Retrieving Metric](https://docs.galtea.ai/sdk/api/metric/get.md): Retrieve a specific metric by its ID.
- [Retrieving Metric By Name](https://docs.galtea.ai/sdk/api/metric/get-by-name.md): Retrieve a specific metric by its name.
- [Deleting Metric](https://docs.galtea.ai/sdk/api/metric/delete.md): Delete a specific metric by its ID.
- [Factual Accuracy](https://docs.galtea.ai/concepts/metric/factual-accuracy.md): Evaluates whether the generated output is factually accurate and adequately addresses the user's input when compared to the reference answer.
- [Resilience To Noise](https://docs.galtea.ai/concepts/metric/resilience-to-noise.md): Measures a language model's robustness to input noise such as typos, OCR/ASR errors, grammatical mistakes, and distracting content.
- [Answer Relevancy](https://docs.galtea.ai/concepts/metric/answer-relevancy.md): Evaluates whether the generated answer is relevant to the user's input.
- [Faithfulness](https://docs.galtea.ai/concepts/metric/faithfulness.md): Evaluates whether the generated output aligns with the retrieved context in a RAG pipeline.
- [Contextual Precision](https://docs.galtea.ai/concepts/metric/contextual-precision.md): Evaluates whether relevant documents in the retrieval context are ranked higher than irrelevant ones.
- [Contextual Recall](https://docs.galtea.ai/concepts/metric/contextual-recall.md): Assesses how comprehensively the retrieved context covers the information needed to produce the expected output.
- [Contextual Relevancy](https://docs.galtea.ai/concepts/metric/contextual-relevancy.md): Measures the quality of your RAG pipeline's retriever by evaluating the overall relevance of the information presented in your retrieval_context for a given input.
- [Knowledge Retention](https://docs.galtea.ai/concepts/metric/knowledge-retention.md): Checks if your product can follow a multi-turn conversation without losing information.
- [Role Adherence](https://docs.galtea.ai/concepts/metric/role-adherence.md): Checks whether your chatbot stays within its defined role across the entire conversation.
- [Conversation Completeness](https://docs.galtea.ai/concepts/metric/conversation-completeness.md): Evaluates whether your chatbot can guide a user to successfully complete their task across multiple turns.
- [Conversation Relevancy](https://docs.galtea.ai/concepts/metric/conversation-relevancy.md): Checks if your product consistently responds in a contextually relevant way during a multi-turn conversation.
- [User Satisfaction](https://docs.galtea.ai/concepts/metric/user-satisfaction.md): Evaluates how satisfied the user was with the conversation. It is a key indicator of user experience.
- [User Objective Accomplished](https://docs.galtea.ai/concepts/metric/user-objective-accomplished.md): Evaluates whether the user's stated objective was successfully and correctly achieved during the conversation.
- [Misuse Resilience](https://docs.galtea.ai/concepts/metric/misuse-resilience.md): Evaluates whether the generated output is resilient to misuse and remains aligned with the product description.
- [Non-Toxic](https://docs.galtea.ai/concepts/metric/non-toxic.md): Evaluates whether your product's responses are free from harmful, offensive, or toxic language.
- [Unbiased](https://docs.galtea.ai/concepts/metric/unbiased.md): Evaluates whether your product's output contains or reinforces harmful bias based on gender, race, or political orientation.
- [Jailbreak Resilience](https://docs.galtea.ai/concepts/metric/jailbreak-resilience.md): Evaluates the AI's ability to provide a safe and appropriate refusal when faced with inputs that are malicious, harmful, or out-of-scope, based on its specific product boundaries.
- [Data Leakage](https://docs.galtea.ai/concepts/metric/data-leakage.md): Evaluates whether the LLM returns content that may include sensitive information. It also checks that the model does not reveal any data explicitly defined as an inability.
- [BLEU](https://docs.galtea.ai/concepts/metric/bleu.md): Primarily used for machine translation evaluation, measuring how many n-grams (phrases of n words) in the candidate translation overlap with those in a set of reference translations.
- [ROUGE](https://docs.galtea.ai/concepts/metric/rouge.md): Evaluates automatic summarization by measuring the longest common subsequence (LCS) that preserves the word order between candidate and reference summaries.
- [METEOR](https://docs.galtea.ai/concepts/metric/meteor.md): Evaluates translation, summarization, and paraphrasing by aligning words using exact matches, stems, or synonyms, computing precision and recall.
- [Text Similarity](https://docs.galtea.ai/concepts/metric/text-similarity.md): Quantifies the overall textual resemblance between a generated summary and a reference summary by using character-level fuzzy matching. This metric accounts for minor variations in wording or structure while still capturing how similar the two texts are at a surface level.
- [Text Match (Deprecated)](https://docs.galtea.ai/concepts/metric/text-match.md): Determines whether the generated text matches the reference with high character-level similarity using fuzzy matching given by the [Text Similarity](/concepts/metric/text-similarity) metric. Returns a binary outcome based on a threshold, making it ideal for simple pass/fail evaluations where exact w…
- [IOU](https://docs.galtea.ai/concepts/metric/iou.md): Measures the spatial overlap between a predicted bounding box and one or more reference boxes. This metric is commonly used in object detection and layout tasks to quantify how well the predicted region aligns with the ground truth.
- [Spatial Match](https://docs.galtea.ai/concepts/metric/spatial-match.md): Performs a binary evaluation of the spatial alignment between a predicted bounding box and one or more reference boxes using the best Intersection over Union (IoU) score. Returns a pass/fail signal based on a threshold, making it ideal for layout-sensitive validation tasks.
- [URL Validation](https://docs.galtea.ai/concepts/metric/url-validation.md): Ensures that all URLs in the model’s output are safe, properly formatted, and resolvable using strict validation and SSRF protection.
- [Tool Correctness](https://docs.galtea.ai/concepts/metric/tool-correctness.md): Measures whether the agent called exactly the expected set of tools for a test case, penalizing missing required tools or using any unnecessary ones.
- [JSON Field Match](https://docs.galtea.ai/concepts/metric/json-field-match.md): Compares JSON objects field by field, checking whether all fields in the expected output exist in the actual output with matching values. Returns the fraction of expected fields that match.
- [JSON Field Match (Normalized)](https://docs.galtea.ai/concepts/metric/json-field-match-normalized.md): Compares JSON objects field by field with case-insensitive and accent-insensitive string matching. Returns the fraction of expected fields that match.
- [Evaluation](https://docs.galtea.ai/concepts/product/version/session/evaluation.md): An evaluation that assesses traces from a session using a metric
- [Evaluation Service](https://docs.galtea.ai/sdk/api/evaluation/service.md): Evaluation Service API methods in the Galtea SDK
- [Run Evaluation](https://docs.galtea.ai/sdk/api/evaluation/run.md): Run an evaluation pipeline for a version, using either your deployed endpoint or a local agent.
- [Create Single-Turn Evaluation](https://docs.galtea.ai/sdk/api/evaluation/create-single-turn.md): Create an evaluation for a single-turn interaction, either from a test case or production data.
- [Create Evaluations](https://docs.galtea.ai/sdk/api/evaluation/create.md): Create evaluations for all traces within a session, or evaluate a single trace using specified metrics.
- [Waiting for Evaluations](https://docs.galtea.ai/sdk/api/evaluation/wait-for.md): Poll evaluations until they leave PENDING status, then return the completed results.
- [Listing Evaluations](https://docs.galtea.ai/sdk/api/evaluation/list.md): List all evaluations associated with a specific session.
- [Retrieving Evaluation](https://docs.galtea.ai/sdk/api/evaluation/get.md): Retrieve a specific evaluation by its ID.
- [Retrying Evaluations](https://docs.galtea.ai/sdk/api/evaluation/retry.md): Retry one or more failed evaluations.
- [Deleting Evaluation](https://docs.galtea.ai/sdk/api/evaluation/delete.md): Delete a specific evaluation by its ID.
- [Jobs Service](https://docs.galtea.ai/sdk/api/job/service.md): Jobs Service API methods in the Galtea SDK
- [Get Job Status](https://docs.galtea.ai/sdk/api/job/get-status.md): Retrieve the current status and progress of an async Galtea job.
- [Cancel Job](https://docs.galtea.ai/sdk/api/job/cancel.md): Cancel a queued or in-flight async Galtea job.
- [User Group](https://docs.galtea.ai/concepts/user-group.md): Organize users and metrics into groups for human evaluation workflows
- [User Groups Service](https://docs.galtea.ai/sdk/api/user-group/service.md): User Groups Service API methods in the Galtea SDK
- [Create User Group](https://docs.galtea.ai/sdk/api/user-group/create.md): Create a new user group.
- [Listing User Groups](https://docs.galtea.ai/sdk/api/user-group/list.md): List user groups with optional filters.
- [Retrieving User Group](https://docs.galtea.ai/sdk/api/user-group/get.md): Get a user group by its ID.
- [Retrieving User Group by Name](https://docs.galtea.ai/sdk/api/user-group/get-by-name.md): Get a user group by its name.
- [Update User Group](https://docs.galtea.ai/sdk/api/user-group/update.md): Update an existing user group.
- [Delete User Group](https://docs.galtea.ai/sdk/api/user-group/delete.md): Delete a user group by its ID.
- [Link Users](https://docs.galtea.ai/sdk/api/user-group/link-users.md): Link users to a user group.
- [Unlink Users](https://docs.galtea.ai/sdk/api/user-group/unlink-users.md): Remove users from a user group.
- [Link Metrics](https://docs.galtea.ai/sdk/api/user-group/link-metrics.md): Link metrics to a user group.
- [Unlink Metrics](https://docs.galtea.ai/sdk/api/user-group/unlink-metrics.md): Remove metrics from a user group.
- [Model](https://docs.galtea.ai/concepts/model.md): A representation of a LLM Model with cost information to calculate cost estimations
- [Model Service](https://docs.galtea.ai/sdk/api/model/service.md): Model Service API methods in the Galtea SDK
- [Create Model](https://docs.galtea.ai/sdk/api/model/create.md): Create a new model for cost tracking.
- [List Models](https://docs.galtea.ai/sdk/api/model/list.md): List models with optional filters.
- [Get Model](https://docs.galtea.ai/sdk/api/model/get.md): Retrieve a specific model by its ID.
- [Get Model By Name](https://docs.galtea.ai/sdk/api/model/get-by-name.md): Retrieve a specific model by its name within the authenticated user's organization.
- [Update Model](https://docs.galtea.ai/sdk/api/model/update.md): Update an existing model.
- [Delete Model](https://docs.galtea.ai/sdk/api/model/delete.md): Delete a specific model by its ID.
- [Health check](https://docs.galtea.ai/api-reference/health-check.md): Health check endpoint to verify API is running. See [Platform Overview](https://docs.galtea.ai/introduction).
- [Get minimum SDK version](https://docs.galtea.ai/api-reference/get-minimum-sdk-version.md): Get minimum supported SDK version of the API and latest published version. See [Platform Overview](https://docs.galtea.ai/introduction).
- [Build info](https://docs.galtea.ai/api-reference/build-info.md): Deployed build metadata (version, commit, build date), so on-prem customers can compare their deployed version with the SaaS. Requires authentication; restricted to admins and organizations with an enterprise subscription.
- [Build info for every deployed service](https://docs.galtea.ai/api-reference/build-info-for-every-deployed-service.md): The API's own build metadata plus one entry per downstream Python service, so on-prem customers and support can see the full component inventory of a deployment at a glance. A downstream service being down never fails this call; it is reported with `status: unreachable` instead. Requires authenticat…
- [List API tokens](https://docs.galtea.ai/api-reference/api-tokens/list-api-tokens.md): List the authenticated user's API tokens. Secrets are never returned — only id, name, keyId and creation date.
- [Create API token](https://docs.galtea.ai/api-reference/api-tokens/create-api-token.md): Create a new named API token for the authenticated user. The key is returned only once and cannot be retrieved later. Creating more than one token requires an Enterprise plan.
- [Revoke API token](https://docs.galtea.ai/api-reference/api-tokens/revoke-api-token.md): Revoke (permanently delete) one of the authenticated user's API tokens. Always allowed, regardless of plan.
- [Rename API token](https://docs.galtea.ai/api-reference/api-tokens/rename-api-token.md): Rename one of the authenticated user's API tokens. Always allowed, regardless of plan.
- [Regenerate API token](https://docs.galtea.ai/api-reference/api-tokens/regenerate-api-token.md): Rotate the secret of one of the authenticated user's API tokens. The old key stops working and the new key is returned only once. Always allowed, regardless of plan.
- [Get current user](https://docs.galtea.ai/api-reference/auth/get-current-user.md): Get the currently authenticated user. See [Registration & Authentication](https://docs.galtea.ai/registration).
- [Get organizations](https://docs.galtea.ai/api-reference/organizations/get-organizations.md): Get list of organizations with pagination and filtering. See [Platform Overview](https://docs.galtea.ai/introduction).
- [Get organization by ID](https://docs.galtea.ai/api-reference/organizations/get-organization-by-id.md): Get a specific organization by ID. See [Platform Overview](https://docs.galtea.ai/introduction).
- [Get credit status](https://docs.galtea.ai/api-reference/organizations/get-credit-status.md): Returns the current credit status for the organization, used for the credit warning badge. See [Platform Overview](https://docs.galtea.ai/introduction).
- [Get user groups](https://docs.galtea.ai/api-reference/user-groups/get-user-groups.md): Get list of user groups with pagination and filtering. See [User Groups](https://docs.galtea.ai/concepts/user-group).
- [Create user group](https://docs.galtea.ai/api-reference/user-groups/create-user-group.md): Create a new user group. See [User Groups](https://docs.galtea.ai/concepts/user-group).
- [Get user group by ID](https://docs.galtea.ai/api-reference/user-groups/get-user-group-by-id.md): Get a specific user group by ID. See [User Groups](https://docs.galtea.ai/concepts/user-group).
- [Delete user group](https://docs.galtea.ai/api-reference/user-groups/delete-user-group.md): Soft delete a user group. See [User Groups](https://docs.galtea.ai/concepts/user-group).
- [Update user group](https://docs.galtea.ai/api-reference/user-groups/update-user-group.md): Update an existing user group. See [User Groups](https://docs.galtea.ai/concepts/user-group).
- [Link users to user group](https://docs.galtea.ai/api-reference/user-groups/link-users-to-user-group.md): Add users to a user group. See [User Groups](https://docs.galtea.ai/concepts/user-group).
- [Unlink users from user group](https://docs.galtea.ai/api-reference/user-groups/unlink-users-from-user-group.md): Remove users from a user group. See [User Groups](https://docs.galtea.ai/concepts/user-group).
- [Link metrics to user group](https://docs.galtea.ai/api-reference/user-groups/link-metrics-to-user-group.md): Add metrics to a user group. See [User Groups](https://docs.galtea.ai/concepts/user-group).
- [Unlink metrics from user group](https://docs.galtea.ai/api-reference/user-groups/unlink-metrics-from-user-group.md): Remove metrics from a user group. See [User Groups](https://docs.galtea.ai/concepts/user-group).
- [Delete multiple user groups](https://docs.galtea.ai/api-reference/user-groups/delete-multiple-user-groups.md): Soft delete multiple user groups by their IDs. See [User Groups](https://docs.galtea.ai/concepts/user-group).
- [Get metrics](https://docs.galtea.ai/api-reference/metrics/get-metrics.md): Get list of metrics with pagination and filtering. See [Metrics](https://docs.galtea.ai/concepts/metric).
- [Create metric](https://docs.galtea.ai/api-reference/metrics/create-metric.md): Create a new metric. See [Metrics](https://docs.galtea.ai/concepts/metric).
- [Get metric by ID](https://docs.galtea.ai/api-reference/metrics/get-metric-by-id.md): Get a specific metric by ID. See [Metrics](https://docs.galtea.ai/concepts/metric).
- [Delete metric](https://docs.galtea.ai/api-reference/metrics/delete-metric.md): Soft delete a metric. See [Metrics](https://docs.galtea.ai/concepts/metric).
- [Update metric](https://docs.galtea.ai/api-reference/metrics/update-metric.md): Update an existing metric. See [Metrics](https://docs.galtea.ai/concepts/metric).
- [Create multiple metrics](https://docs.galtea.ai/api-reference/metrics/create-multiple-metrics.md): Create multiple metrics at once. See [Metrics](https://docs.galtea.ai/concepts/metric).
- [Delete multiple metrics](https://docs.galtea.ai/api-reference/metrics/delete-multiple-metrics.md): Soft delete multiple metrics by their IDs. See [Metrics](https://docs.galtea.ai/concepts/metric).
- [Count replay candidates per product for a metric revision](https://docs.galtea.ai/api-reference/metrics/count-replay-candidates-per-product-for-a-metric-revision.md): For each requested product, returns how many historical evaluations in this metric's group would be replayed against this revision. Any `(sessionId, inferenceResultId)` pair already evaluated with this metric is excluded. Products with no candidates return `count: 0`.
- [Get human annotation count and optimization eligibility](https://docs.galtea.ai/api-reference/metrics/get-human-annotation-count-and-optimization-eligibility.md): Returns the optimization-eligibility snapshot for a metric.
- [Optimize metric](https://docs.galtea.ai/api-reference/metrics/optimize-metric.md): Creates an optimized copy of a metric by sending its human-annotated evaluations to the metrics-generator service, which uses the gap between AI and human scores to produce a better judge prompt. Only FULL_PROMPT and PARTIAL_PROMPT metrics owned by an organization can be optimized. Rejected with 400…
- [Generate or complete metric configuration with AI](https://docs.galtea.ai/api-reference/metrics/generate-or-complete-metric-configuration-with-ai.md): Two modes, selected by the request body:
- [Revise metric configuration with AI ("Update With AI")](https://docs.galtea.ai/api-reference/metrics/revise-metric-configuration-with-ai-"update-with-ai".md): Given a metric config the caller already has (name, description, judge prompt, evaluation params, evaluation type) plus one line of feedback, returns a revised judge prompt, evaluation parameters, and description. Persists nothing — the caller decides whether to apply the result.
- [Get specifications](https://docs.galtea.ai/api-reference/specifications/get-specifications.md): Get list of specifications with pagination and filtering. See [Specifications](https://docs.galtea.ai/concepts/product/specification).
- [Create specification](https://docs.galtea.ai/api-reference/specifications/create-specification.md): Create a new specification. See [Specifications](https://docs.galtea.ai/concepts/product/specification).
- [Get specification by ID](https://docs.galtea.ai/api-reference/specifications/get-specification-by-id.md): Get a specific specification by ID. See [Specifications](https://docs.galtea.ai/concepts/product/specification).
- [Delete specification](https://docs.galtea.ai/api-reference/specifications/delete-specification.md): Soft delete a specification. See [Specifications](https://docs.galtea.ai/concepts/product/specification).
- [Update specification](https://docs.galtea.ai/api-reference/specifications/update-specification.md): Update an existing specification. See [Specifications](https://docs.galtea.ai/concepts/product/specification).
- [Create multiple specifications](https://docs.galtea.ai/api-reference/specifications/create-multiple-specifications.md): Create multiple specifications at once. See [Specifications](https://docs.galtea.ai/concepts/product/specification).
- [Delete multiple specifications](https://docs.galtea.ai/api-reference/specifications/delete-multiple-specifications.md): Soft delete multiple specifications by their IDs. See [Specifications](https://docs.galtea.ai/concepts/product/specification).
- [Get linked metrics](https://docs.galtea.ai/api-reference/specifications/get-linked-metrics.md): Get all metrics linked to a specification. See [Specifications](https://docs.galtea.ai/concepts/product/specification).
- [Link metrics to specification](https://docs.galtea.ai/api-reference/specifications/link-metrics-to-specification.md): Link one or more metrics to a specification. See [Specifications](https://docs.galtea.ai/concepts/product/specification).
- [Unlink metrics from specification](https://docs.galtea.ai/api-reference/specifications/unlink-metrics-from-specification.md): Unlink one or more metrics from a specification. See [Specifications](https://docs.galtea.ai/concepts/product/specification).
- [Get linked datasets](https://docs.galtea.ai/api-reference/specifications/get-linked-datasets.md): Get all datasets linked to a specification. See [Specifications](https://docs.galtea.ai/concepts/product/specification).
- [Link datasets to specification](https://docs.galtea.ai/api-reference/specifications/link-datasets-to-specification.md): Link one or more datasets to a specification. See [Specifications](https://docs.galtea.ai/concepts/product/specification).
- [Unlink datasets from specification](https://docs.galtea.ai/api-reference/specifications/unlink-datasets-from-specification.md): Unlink one or more datasets from a specification. See [Specifications](https://docs.galtea.ai/concepts/product/specification).
- [Generate specification configuration](https://docs.galtea.ai/api-reference/specifications/generate-specification-configuration.md): Uses AI to rewrite a rough or brief note into a properly written specification description and suggest its classification (type, test type, test variant) in a single request. Nothing is persisted — the caller decides which fields to apply and creates the specification explicitly. See [Specifications…
- [Get models](https://docs.galtea.ai/api-reference/models/get-models.md): Get list of models with pagination and filtering. See [Models](https://docs.galtea.ai/concepts/model).
- [Create model](https://docs.galtea.ai/api-reference/models/create-model.md): Create a new model. See [Models](https://docs.galtea.ai/concepts/model).
- [Get model by ID](https://docs.galtea.ai/api-reference/models/get-model-by-id.md): Get a specific model by ID. See [Models](https://docs.galtea.ai/concepts/model).
- [Delete model](https://docs.galtea.ai/api-reference/models/delete-model.md): Soft delete a model. See [Models](https://docs.galtea.ai/concepts/model).
- [Update model](https://docs.galtea.ai/api-reference/models/update-model.md): Update an existing model. See [Models](https://docs.galtea.ai/concepts/model).
- [Delete multiple models](https://docs.galtea.ai/api-reference/models/delete-multiple-models.md): Soft delete multiple models by their IDs. See [Models](https://docs.galtea.ai/concepts/model).
- [Get products](https://docs.galtea.ai/api-reference/products/get-products.md): Get list of products with pagination and filtering options. See [Products](https://docs.galtea.ai/concepts/product).
- [Create product](https://docs.galtea.ai/api-reference/products/create-product.md): Create a new product. See [Products](https://docs.galtea.ai/concepts/product).
- [List distinct product tags](https://docs.galtea.ai/api-reference/products/list-distinct-product-tags.md): Returns the sorted, distinct set of tags used across products in the requested organizations. Tags are returned lowercase and trimmed. Powers tag-suggestion UIs in the dashboard and the product-list tag filter.
- [Get product by ID](https://docs.galtea.ai/api-reference/products/get-product-by-id.md): Get a specific product by ID. See [Products](https://docs.galtea.ai/concepts/product).
- [Delete product](https://docs.galtea.ai/api-reference/products/delete-product.md): Soft delete a product. See [Products](https://docs.galtea.ai/concepts/product).
- [Update product](https://docs.galtea.ai/api-reference/products/update-product.md): Update an existing product. See [Products](https://docs.galtea.ai/concepts/product).
- [Delete multiple products](https://docs.galtea.ai/api-reference/products/delete-multiple-products.md): Soft delete multiple products by their IDs. See [Products](https://docs.galtea.ai/concepts/product).
- [Generate product configuration using AI](https://docs.galtea.ai/api-reference/products/generate-product-configuration-using-ai.md): Uses AI to generate a refined product description and testable specifications from a product name and user description. Optionally accepts product specification files (documents, images, audio, video, code) to enrich the generation. See [Products](https://docs.galtea.ai/concepts/product).
- [Cross-check a document against an existing product's specifications](https://docs.galtea.ai/api-reference/products/cross-check-a-document-against-an-existing-products-specifications.md): Uploads one or more documents (PRD, spec, design doc, etc.), generates candidate specifications from them using the product's existing description as the generation base, and cross-checks each candidate against the product's CURRENT specifications. Returns classified suggestions — additions (`new`),…
- [Get versions](https://docs.galtea.ai/api-reference/versions/get-versions.md): Get list of versions with pagination and filtering options. See [Versions](https://docs.galtea.ai/concepts/product/version).
- [Create version](https://docs.galtea.ai/api-reference/versions/create-version.md): Create a new version. See [Versions](https://docs.galtea.ai/concepts/product/version).
- [Get version by ID](https://docs.galtea.ai/api-reference/versions/get-version-by-id.md): Get a specific version by ID. See [Versions](https://docs.galtea.ai/concepts/product/version).
- [Delete version](https://docs.galtea.ai/api-reference/versions/delete-version.md): Soft delete a version. See [Versions](https://docs.galtea.ai/concepts/product/version).
- [Update version](https://docs.galtea.ai/api-reference/versions/update-version.md): Update an existing version. See [Versions](https://docs.galtea.ai/concepts/product/version).
- [List metrics annotated with compatibility for a version](https://docs.galtea.ai/api-reference/versions/list-metrics-annotated-with-compatibility-for-a-version.md): Returns evaluable metrics annotated with whether they can be satisfied by the version's product metadata and conversation endpoint connection output mapping, plus a `relevance` ranking against the tests the evaluation will run against. Span-dependent and runtime-only params are out of scope and trea…
- [Delete multiple versions](https://docs.galtea.ai/api-reference/versions/delete-multiple-versions.md): Soft delete multiple versions by their IDs. See [Versions](https://docs.galtea.ai/concepts/product/version).
- [Get monitors](https://docs.galtea.ai/api-reference/monitors/get-monitors.md): Get list of monitors with pagination and filtering. See [Monitors](https://docs.galtea.ai/concepts/product/monitor).
- [Create monitor](https://docs.galtea.ai/api-reference/monitors/create-monitor.md): Create a new monitor. See [Monitors](https://docs.galtea.ai/concepts/product/monitor).
- [Get monitor by ID](https://docs.galtea.ai/api-reference/monitors/get-monitor-by-id.md): Get a specific monitor by ID. See [Monitors](https://docs.galtea.ai/concepts/product/monitor).
- [Delete monitor](https://docs.galtea.ai/api-reference/monitors/delete-monitor.md): Soft delete a monitor. See [Monitors](https://docs.galtea.ai/concepts/product/monitor).
- [Update monitor](https://docs.galtea.ai/api-reference/monitors/update-monitor.md): Update an existing monitor. Pause or resume a monitor by setting status to PAUSED or ACTIVE. See [Monitors](https://docs.galtea.ai/concepts/product/monitor).
- [Get monitor results](https://docs.galtea.ai/api-reference/monitors/get-monitor-results.md): Aggregated results for a monitor over a trailing window (default 7 days, bucketed by day): per-metric-family sampling-weighted score series with 95% confidence intervals, the worst metric family, metric-revision and sampling-change markers, current-cycle credit spend, and the scored/waiting session…
- [Preview monitor content-filter matches](https://docs.galtea.ai/api-reference/monitors/preview-monitor-content-filter-matches.md): Read-only preview for a CANDIDATE monitor config: how many and which recent past sessions the given content filter and sampling percentage would select, over a trailing window. Runs no evaluations, spends no credits, and writes nothing (no processed marks). Use it while creating or editing a monitor…
- [Delete multiple monitors](https://docs.galtea.ai/api-reference/monitors/delete-multiple-monitors.md): Soft delete multiple monitors by their IDs. See [Monitors](https://docs.galtea.ai/concepts/product/monitor).
- [Get endpoint connections](https://docs.galtea.ai/api-reference/endpoint-connections/get-endpoint-connections.md): Get list of endpoint connections with pagination and filtering. See [Endpoint Connections](https://docs.galtea.ai/concepts/product/endpoint-connection).
- [Create endpoint connection](https://docs.galtea.ai/api-reference/endpoint-connections/create-endpoint-connection.md): Create a new endpoint connection. See [Endpoint Connections](https://docs.galtea.ai/concepts/product/endpoint-connection).
- [Get endpoint connection by ID](https://docs.galtea.ai/api-reference/endpoint-connections/get-endpoint-connection-by-id.md): Get a specific endpoint connection by ID. See [Endpoint Connections](https://docs.galtea.ai/concepts/product/endpoint-connection).
- [Delete endpoint connection](https://docs.galtea.ai/api-reference/endpoint-connections/delete-endpoint-connection.md): Soft delete an endpoint connection. See [Endpoint Connections](https://docs.galtea.ai/concepts/product/endpoint-connection).
- [Update endpoint connection](https://docs.galtea.ai/api-reference/endpoint-connections/update-endpoint-connection.md): Update an existing endpoint connection. See [Endpoint Connections](https://docs.galtea.ai/concepts/product/endpoint-connection).
- [Test endpoint connection](https://docs.galtea.ai/api-reference/endpoint-connections/test-endpoint-connection.md): Test an endpoint connection by making a sample request. Can be used in two modes: (1) Without an ID — all connection fields are required (creation flow). (2) With an ID — fetches the stored connection and applies any provided fields as overrides (update flow). See [Endpoint Connections](https://docs…
- [Parse a cURL command into endpoint connection fields](https://docs.galtea.ai/api-reference/endpoint-connections/parse-a-curl-command-into-endpoint-connection-fields.md): Parse a raw cURL command into best-effort endpoint-connection fields (URL, HTTP method, headers, auth type/token, request body, and a derived input template). The parse is best-effort: a command that cannot be fully parsed still returns the partial entity together with a structured `errors` array de…
- [Delete multiple endpoint connections](https://docs.galtea.ai/api-reference/endpoint-connections/delete-multiple-endpoint-connections.md): Soft delete multiple endpoint connections by their IDs. See [Endpoint Connections](https://docs.galtea.ai/concepts/product/endpoint-connection).
- [Get datasets](https://docs.galtea.ai/api-reference/datasets/get-datasets.md): Get list of datasets with pagination and filtering options. See [Datasets](https://docs.galtea.ai/concepts/product/dataset).
- [Create dataset](https://docs.galtea.ai/api-reference/datasets/create-dataset.md): Create a new dataset. See [Datasets](https://docs.galtea.ai/concepts/product/dataset).
- [Get dataset types used by the organization](https://docs.galtea.ai/api-reference/datasets/get-dataset-types-used-by-the-organization.md): Retrieves the non-repeated dataset types of all the products of the user's organization. See [Datasets](https://docs.galtea.ai/concepts/product/dataset).
- [Extend a generated dataset with more cases](https://docs.galtea.ai/api-reference/datasets/extend-a-generated-dataset-with-more-cases.md): Re-run the generator that originally produced this dataset (scenario, red teaming, or gold standard) and append the new cases to it. Only datasets Galtea generated from a specification or ground-truth document can be extended. See [Datasets](https://docs.galtea.ai/concepts/product/dataset).
- [Create multiple datasets](https://docs.galtea.ai/api-reference/datasets/create-multiple-datasets.md): Create multiple datasets at once. See [Datasets](https://docs.galtea.ai/concepts/product/dataset).
- [Delete multiple datasets](https://docs.galtea.ai/api-reference/datasets/delete-multiple-datasets.md): Soft delete multiple datasets by their IDs. See [Datasets](https://docs.galtea.ai/concepts/product/dataset).
- [Get dataset by ID](https://docs.galtea.ai/api-reference/datasets/get-dataset-by-id.md): Get a specific dataset by ID. See [Datasets](https://docs.galtea.ai/concepts/product/dataset).
- [Delete dataset](https://docs.galtea.ai/api-reference/datasets/delete-dataset.md): Soft delete a dataset. See [Datasets](https://docs.galtea.ai/concepts/product/dataset).
- [Update dataset](https://docs.galtea.ai/api-reference/datasets/update-dataset.md): Apply a partial update to an existing dataset. See [Datasets](https://docs.galtea.ai/concepts/product/dataset).
- [Generate dataset configuration from specifications](https://docs.galtea.ai/api-reference/datasets/generate-dataset-configuration-from-specifications.md): Derives dataset type, variant, and name from specifications (rule-based).
- [Get test cases](https://docs.galtea.ai/api-reference/test-cases/get-test-cases.md): Get list of test cases with pagination and filtering options. See [Datasets](https://docs.galtea.ai/concepts/product/dataset).
- [Create test case](https://docs.galtea.ai/api-reference/test-cases/create-test-case.md): Create a new test case. See [Datasets](https://docs.galtea.ai/concepts/product/dataset).
- [Get test case languages](https://docs.galtea.ai/api-reference/test-cases/get-test-case-languages.md): Get all available languages for test cases. See [Datasets](https://docs.galtea.ai/concepts/product/dataset).
- [Export test cases as CSV](https://docs.galtea.ai/api-reference/test-cases/export-test-cases-as-csv.md): Generate a CSV from the current DB state of the given test cases, upload to storage, and return a presigned download URL. See [Datasets](https://docs.galtea.ai/concepts/product/dataset).
- [Get test case by ID](https://docs.galtea.ai/api-reference/test-cases/get-test-case-by-id.md): Get a specific test case by ID. See [Datasets](https://docs.galtea.ai/concepts/product/dataset).
- [Delete test case](https://docs.galtea.ai/api-reference/test-cases/delete-test-case.md): Soft delete a test case. See [Datasets](https://docs.galtea.ai/concepts/product/dataset).
- [Update test case](https://docs.galtea.ai/api-reference/test-cases/update-test-case.md): Update an existing test case. See [Datasets](https://docs.galtea.ai/concepts/product/dataset).
- [Delete multiple test cases](https://docs.galtea.ai/api-reference/test-cases/delete-multiple-test-cases.md): Soft delete multiple test cases by their IDs. See [Datasets](https://docs.galtea.ai/concepts/product/dataset).
- [Augment test cases](https://docs.galtea.ai/api-reference/test-cases/augment-test-cases.md): Submit test cases for augmentation using few-shot learning. The API automatically selects up to 5 random test cases from the given dataset as few-shot examples. See [Datasets](https://docs.galtea.ai/concepts/product/dataset).
- [Get augmentation task status](https://docs.galtea.ai/api-reference/test-cases/get-augmentation-task-status.md): Retrieve the status of an augmentation task. See [Datasets](https://docs.galtea.ai/concepts/product/dataset).
- [Count replay candidates per product for a test case revision](https://docs.galtea.ai/api-reference/test-cases/count-replay-candidates-per-product-for-a-test-case-revision.md): For each requested product, returns how many historical evaluations in this test case's revision family would be replayed against this revision. A candidate is a distinct `(version, metric)` combination that any revision in the family was evaluated with (production sessions excluded) and whose versi…
- [Get sessions](https://docs.galtea.ai/api-reference/sessions/get-sessions.md): Get list of sessions with pagination and filtering. See [Sessions](https://docs.galtea.ai/concepts/product/version/session).
- [Create session](https://docs.galtea.ai/api-reference/sessions/create-session.md): Create a new session. See [Sessions](https://docs.galtea.ai/concepts/product/version/session).
- [Get session by ID](https://docs.galtea.ai/api-reference/sessions/get-session-by-id.md): Get a specific session by ID. See [Sessions](https://docs.galtea.ai/concepts/product/version/session).
- [Delete session](https://docs.galtea.ai/api-reference/sessions/delete-session.md): Soft delete a session. See [Sessions](https://docs.galtea.ai/concepts/product/version/session).
- [Update session](https://docs.galtea.ai/api-reference/sessions/update-session.md): Update an existing session. See [Sessions](https://docs.galtea.ai/concepts/product/version/session).
- [List metrics annotated with compatibility for a session](https://docs.galtea.ai/api-reference/sessions/list-metrics-annotated-with-compatibility-for-a-session.md): Returns evaluable metrics annotated with whether they can be satisfied by the session's product metadata and test-case availability, plus a `relevance` ranking derived from the session's test case's test (`linked`/`matching`/`none`). A session evaluation scores output that is already stored, so the…
- [Finish session](https://docs.galtea.ai/api-reference/sessions/finish-session.md): Marks a session as COMPLETED (stoppingReason provided) or FAILED (error provided). At least one of stoppingReason or error must be provided. See [Sessions](https://docs.galtea.ai/concepts/product/version/session).
- [Delete multiple sessions](https://docs.galtea.ai/api-reference/sessions/delete-multiple-sessions.md): Soft delete multiple sessions by their IDs. See [Sessions](https://docs.galtea.ai/concepts/product/version/session).
- [Generate next user message](https://docs.galtea.ai/api-reference/sessions/generate-next-user-message.md): Simulate the next user message in a conversation based on the provided scenario and turns. See [Sessions](https://docs.galtea.ai/concepts/product/version/session).
- [Import sessions from a Langfuse trace export](https://docs.galtea.ai/api-reference/sessions/import-sessions-from-a-langfuse-trace-export.md): Imports production sessions from a Langfuse export. The content is handed to a background BullMQ job; the response is the `jobId` to poll on `GET /jobs/{jobId}/status`. Semantic validation (Langfuse shape, drop rules) happens in the job, so a syntactically valid upload is accepted with `202` and rej…
- [Get traces](https://docs.galtea.ai/api-reference/traces/get-traces.md): Get list of traces with pagination and filtering. See [Traces](https://docs.galtea.ai/concepts/product/version/session/trace). The REST path `/inferenceResults` and the `inferenceResult*` JSON fields keep the old name of this entity.
- [Create trace](https://docs.galtea.ai/api-reference/traces/create-trace.md): Create a new trace. Identify the session with exactly one of `sessionId` or `sessionCustomId`. With `sessionCustomId` (your own conversation id) an existing session with that custom id is found and appended to: provide either `versionId` or `productId` as the anchor (if both are given, `versionId` w…
- [Get aggregated performance data](https://docs.galtea.ai/api-reference/traces/get-aggregated-performance-data.md): Get aggregated performance metrics data. See [Traces](https://docs.galtea.ai/concepts/product/version/session/trace). The REST path `/inferenceResults` and the `inferenceResult*` JSON fields keep the old name of this entity.
- [Get trace by ID](https://docs.galtea.ai/api-reference/traces/get-trace-by-id.md): Get a specific trace by ID. See [Traces](https://docs.galtea.ai/concepts/product/version/session/trace). The REST path `/inferenceResults` and the `inferenceResult*` JSON fields keep the old name of this entity.
- [Delete trace](https://docs.galtea.ai/api-reference/traces/delete-trace.md): Soft delete a trace. See [Traces](https://docs.galtea.ai/concepts/product/version/session/trace). The REST path `/inferenceResults` and the `inferenceResult*` JSON fields keep the old name of this entity.
- [Update trace](https://docs.galtea.ai/api-reference/traces/update-trace.md): Update an existing trace. See [Traces](https://docs.galtea.ai/concepts/product/version/session/trace). The REST path `/inferenceResults` and the `inferenceResult*` JSON fields keep the old name of this entity.
- [Create traces batch](https://docs.galtea.ai/api-reference/traces/create-traces-batch.md): Create multiple traces from conversation turns. Identify the session with exactly one of `sessionId` or `sessionCustomId` (same find-existing semantics as `POST /inferenceResults`). See [Traces](https://docs.galtea.ai/concepts/product/version/session/trace). The REST path `/inferenceResults` and the…
- [Delete multiple traces](https://docs.galtea.ai/api-reference/traces/delete-multiple-traces.md): Soft delete multiple traces by their IDs. See [Traces](https://docs.galtea.ai/concepts/product/version/session/trace). The REST path `/inferenceResults` and the `inferenceResult*` JSON fields keep the old name of this entity.
- [Generate traces from test cases](https://docs.galtea.ai/api-reference/traces/generate-traces-from-test-cases.md): Triggers async inference generation for specified test cases using the version's endpoint connection. Provide either `versionId` or `productId`. When `productId` is given without a `versionId`, the product's latest properly configured version (one with a conversation-endpoint, phone, or WebRTC conne…
- [Get spans](https://docs.galtea.ai/api-reference/spans/get-spans.md): Get a list of spans with filtering and pagination. See [Spans](https://docs.galtea.ai/sdk/api/span/service). These endpoints serve spans, the steps inside a trace. Their REST path `/traces` keeps the old name of this entity.
- [Create span](https://docs.galtea.ai/api-reference/spans/create-span.md): Create a new span for a tool/function call. See [Spans](https://docs.galtea.ai/sdk/api/span/service). These endpoints serve spans, the steps inside a trace. Their REST path `/traces` keeps the old name of this entity.
- [Get span by ID](https://docs.galtea.ai/api-reference/spans/get-span-by-id.md): Get a specific span by its ID. See [Spans](https://docs.galtea.ai/sdk/api/span/service). These endpoints serve spans, the steps inside a trace. Their REST path `/traces` keeps the old name of this entity.
- [Delete span](https://docs.galtea.ai/api-reference/spans/delete-span.md): Soft delete a span by its ID. See [Spans](https://docs.galtea.ai/sdk/api/span/service). These endpoints serve spans, the steps inside a trace. Their REST path `/traces` keeps the old name of this entity.
- [Create spans batch](https://docs.galtea.ai/api-reference/spans/create-spans-batch.md): Create multiple spans in a single API call (transactional). See [Spans](https://docs.galtea.ai/sdk/api/span/service). These endpoints serve spans, the steps inside a trace. Their REST path `/traces` keeps the old name of this entity.
- [Delete multiple spans](https://docs.galtea.ai/api-reference/spans/delete-multiple-spans.md): Soft delete multiple spans by their IDs. See [Spans](https://docs.galtea.ai/sdk/api/span/service). These endpoints serve spans, the steps inside a trace. Their REST path `/traces` keeps the old name of this entity.
- [Create evaluations from session](https://docs.galtea.ai/api-reference/evaluations/create-evaluations-from-session.md): Create evaluations from a session. See [Evaluations](https://docs.galtea.ai/concepts/product/version/session/evaluation).
- [Evaluate multiple sessions in one call](https://docs.galtea.ai/api-reference/evaluations/evaluate-multiple-sessions-in-one-call.md): Batch-evaluate existing sessions in a single call. Pick exactly one mode: (a) `sessionIds` — explicit list of session IDs; (b) `versionId` — every session attached to that version. Each selected session is evaluated by the same logic as `POST /evaluations/fromSession`, so the traces that already liv…
- [Create evaluations for a single trace](https://docs.galtea.ai/api-reference/evaluations/create-evaluations-for-a-single-trace.md): Create evaluations for a specific turn in a conversation. This is useful for production monitoring where you want to evaluate turn-by-turn performance. See [Evaluations](https://docs.galtea.ai/concepts/product/version/session/evaluation).
- [Create single-turn evaluations](https://docs.galtea.ai/api-reference/evaluations/create-single-turn-evaluations.md): Create evaluations for single-turn interactions. See [Evaluations](https://docs.galtea.ai/concepts/product/version/session/evaluation).
- [Retry failed evaluations](https://docs.galtea.ai/api-reference/evaluations/retry-failed-evaluations.md): Retry one or more failed evaluations. Non-admin users are limited by EVALUATION_MAX_RETRIES. See [Evaluations](https://docs.galtea.ai/concepts/product/version/session/evaluation).
- [Evaluate a version](https://docs.galtea.ai/api-reference/evaluations/evaluate-a-version.md): Automatically evaluates a version by resolving its product's specifications, their linked metrics, and their linked tests. Creates inference generation jobs for every test case across all linked tests. Specifications without tests or without metrics are silently skipped. Provide either `versionId` o…
- [Replay evaluations onto a new metric revision](https://docs.galtea.ai/api-reference/evaluations/replay-evaluations-onto-a-new-metric-revision.md): Re-runs historical evaluations that used any metric in `metricGroupId` against the new metric revision `newMetricId`, scoped to the given products. Idempotent: any `(sessionId, inferenceResultId)` pair that already has an evaluation on `newMetricId` is skipped.
- [Delete multiple evaluations](https://docs.galtea.ai/api-reference/evaluations/delete-multiple-evaluations.md): Soft delete multiple evaluations by their IDs. See [Evaluations](https://docs.galtea.ai/concepts/product/version/session/evaluation).
- [Get pending human evaluations](https://docs.galtea.ai/api-reference/evaluations/get-pending-human-evaluations.md): Get list of pending human evaluations that the authenticated user can evaluate based on their user groups. See [Evaluations](https://docs.galtea.ai/concepts/product/version/session/evaluation).
- [Get completed human evaluations](https://docs.galtea.ai/api-reference/evaluations/get-completed-human-evaluations.md): Get list of human evaluations completed by the authenticated user. See [Evaluations](https://docs.galtea.ai/concepts/product/version/session/evaluation).
- [Claim an evaluation for human review or annotation](https://docs.galtea.ai/api-reference/evaluations/claim-an-evaluation-for-human-review-or-annotation.md): Claim an evaluation to prevent concurrent editing. For HUMAN_EVALUATION metrics, enforces user group permissions (admins skip). For other metrics, works as an annotation claim open to all org members. Works on any evaluation status. Sets humanEvaluatorStartedAt timestamp. See [Evaluations](https://d…
- [Release a claimed evaluation or annotation](https://docs.galtea.ai/api-reference/evaluations/release-a-claimed-evaluation-or-annotation.md): Release a previously claimed evaluation or annotation without submitting a score. Works on any evaluation status. Clears humanEvaluatorStartedAt. See [Evaluations](https://docs.galtea.ai/concepts/product/version/session/evaluation).
- [Submit a human evaluation or annotation score](https://docs.galtea.ai/api-reference/evaluations/submit-a-human-evaluation-or-annotation-score.md): Submit a score and optional reason. For HUMAN_EVALUATION metrics, enforces user group permissions and updates both score sets. For PENDING_HUMAN evaluations, also sets status to SUCCESS. For other metrics, works as an annotation — writes only humanScore/humanReason/humanEvaluatorFinishedAt, leaving…
- [Edit a submitted human evaluation](https://docs.galtea.ai/api-reference/evaluations/edit-a-submitted-human-evaluation.md): Edit the score and reason for a previously submitted human evaluation. Only the original evaluator can edit. See [Evaluations](https://docs.galtea.ai/concepts/product/version/session/evaluation).
- [Get evaluation by ID](https://docs.galtea.ai/api-reference/evaluations/get-evaluation-by-id.md): Get a specific evaluation by ID. See [Evaluations](https://docs.galtea.ai/concepts/product/version/session/evaluation).
- [Delete evaluation](https://docs.galtea.ai/api-reference/evaluations/delete-evaluation.md): Soft delete an evaluation. See [Evaluations](https://docs.galtea.ai/concepts/product/version/session/evaluation).
- [Get evaluations](https://docs.galtea.ai/api-reference/evaluations/get-evaluations.md): Get list of evaluations with pagination and filtering. See [Evaluations](https://docs.galtea.ai/concepts/product/version/session/evaluation).
- [Replay evaluations onto a new test case revision](https://docs.galtea.ai/api-reference/evaluations/replay-evaluations-onto-a-new-test-case-revision.md): Re-runs the evaluations that any revision in `testCaseGroupId` was scored with against the new test case revision `newTestCaseId`, scoped to the given products. Because an evaluation is bound to a test case only through its session, fresh inference is generated for the new revision on each version t…
- [Get analytics data](https://docs.galtea.ai/api-reference/analytics/get-analytics-data.md): Get analytics data for a product with optional filtering. See [Platform Overview](https://docs.galtea.ai/introduction).
- [Export analytics data](https://docs.galtea.ai/api-reference/analytics/export-analytics-data.md): Export analytics data for a product with optional filtering. See [Platform Overview](https://docs.galtea.ai/introduction).
- [Get analytics insights for a version](https://docs.galtea.ai/api-reference/analytics/get-analytics-insights-for-a-version.md): Computes deterministic red flags / proactive insights (low metric scores, specification coverage gaps) for a single version, plus a fail-open LLM-generated narrative summary. See [Platform Overview](https://docs.galtea.ai/introduction).
- [Get cross-version analytics comparison insights](https://docs.galtea.ai/api-reference/analytics/get-cross-version-analytics-comparison-insights.md): Computes deterministic red flags / proactive insights across versions (metric degradation, metric improvement, cost outlier, latency outlier), plus a fail-open LLM-generated narrative summary. When versionIds is omitted, all versions present in the analytics data are compared. See [Platform Overview…
- [Generate upload presigned URL](https://docs.galtea.ai/api-reference/storage/generate-upload-presigned-url.md): Generate a presigned URL for uploading files to storage. See [Platform Overview](https://docs.galtea.ai/introduction).
- [Generate download presigned URL](https://docs.galtea.ai/api-reference/storage/generate-download-presigned-url.md): Generate a presigned URL for downloading files from storage. See [Platform Overview](https://docs.galtea.ai/introduction).
- [Get evaluator models](https://docs.galtea.ai/api-reference/evaluator-models/get-evaluator-models.md): Get list of evaluator models with filtering options. See [Models](https://docs.galtea.ai/concepts/model).
- [Get job status](https://docs.galtea.ai/api-reference/jobs/get-job-status.md): Retrieve the status of an async job (e.g., inference generation). Returns the job state, progress, result, and any error information.
- [Cancel a job](https://docs.galtea.ai/api-reference/jobs/cancel-a-job.md): Cancel a queued or in-flight async job (e.g., inference generation). Use this to stop a doomed batch instead of waiting for every unit to fail individually.
- [Validate credentials for OTel ingestion](https://docs.galtea.ai/api-reference/otel/validate-credentials-for-otel-ingestion.md): Validates the customer's API key and returns the user ID via x-customer-id header. Used by the Istio gateway ext-authz filter to authenticate OTel data ingestion requests.
- [Ingest OpenTelemetry spans (OTLP/JSON)](https://docs.galtea.ai/api-reference/otel/ingest-opentelemetry-spans-otlpjson.md): Receives an OTLP/JSON trace payload and persists its spans as Galtea Span records. Authenticated via standard API key (processAccessTokenMiddleware); the authenticated user is the tenant and RBAC applies. Any payload customer.id resource attribute is ignored on this public path.
- [Get phone connections](https://docs.galtea.ai/api-reference/phone-connections/get-phone-connections.md): Get list of phone connections with pagination and filtering. See [Phone Connections](https://docs.galtea.ai/concepts/product/phone-connection).
- [Create phone connection](https://docs.galtea.ai/api-reference/phone-connections/create-phone-connection.md): Create a new phone connection. See [Phone Connections](https://docs.galtea.ai/concepts/product/phone-connection).
- [Get phone connection by ID](https://docs.galtea.ai/api-reference/phone-connections/get-phone-connection-by-id.md): Get a specific phone connection by ID. See [Phone Connections](https://docs.galtea.ai/concepts/product/phone-connection).
- [Delete phone connection](https://docs.galtea.ai/api-reference/phone-connections/delete-phone-connection.md): Soft delete a phone connection. See [Phone Connections](https://docs.galtea.ai/concepts/product/phone-connection).
- [Update phone connection](https://docs.galtea.ai/api-reference/phone-connections/update-phone-connection.md): Update an existing phone connection. See [Phone Connections](https://docs.galtea.ai/concepts/product/phone-connection).
- [Delete multiple phone connections](https://docs.galtea.ai/api-reference/phone-connections/delete-multiple-phone-connections.md): Soft delete multiple phone connections by their IDs. See [Phone Connections](https://docs.galtea.ai/concepts/product/phone-connection).
- [Get WebRTC connections](https://docs.galtea.ai/api-reference/web-rtc-connections/get-webrtc-connections.md): Get list of WebRTC connections with pagination and filtering. See [WebRTC Connections](https://docs.galtea.ai/concepts/product/webrtc-connection).
- [Create WebRTC connection](https://docs.galtea.ai/api-reference/web-rtc-connections/create-webrtc-connection.md): Create a new WebRTC connection. See [WebRTC Connections](https://docs.galtea.ai/concepts/product/webrtc-connection).
- [Get WebRTC connection by ID](https://docs.galtea.ai/api-reference/web-rtc-connections/get-webrtc-connection-by-id.md): Get a specific WebRTC connection by ID. See [WebRTC Connections](https://docs.galtea.ai/concepts/product/webrtc-connection).
- [Delete WebRTC connection](https://docs.galtea.ai/api-reference/web-rtc-connections/delete-webrtc-connection.md): Soft delete a WebRTC connection. See [WebRTC Connections](https://docs.galtea.ai/concepts/product/webrtc-connection).
- [Update WebRTC connection](https://docs.galtea.ai/api-reference/web-rtc-connections/update-webrtc-connection.md): Update an existing WebRTC connection. See [WebRTC Connections](https://docs.galtea.ai/concepts/product/webrtc-connection).
- [Delete multiple WebRTC connections](https://docs.galtea.ai/api-reference/web-rtc-connections/delete-multiple-webrtc-connections.md): Soft delete multiple WebRTC connections by their IDs. See [WebRTC Connections](https://docs.galtea.ai/concepts/product/webrtc-connection).
- [Create comment](https://docs.galtea.ai/api-reference/comments/create-comment.md): Adds a free-form annotation to a trace, for error analysis outside the metric-bound evaluation flow. A trace can hold many comments.
- [List distinct comment labels](https://docs.galtea.ai/api-reference/comments/list-distinct-comment-labels.md): Returns the sorted, distinct labels used on the comments of the requested products, lowercase and trimmed. Labels are product-scoped: this is the reuse list a reviewer picks from when annotating a turn, and the options of the session-list label filter. `productIds` is required; a product the caller…
- [Delete comment](https://docs.galtea.ai/api-reference/comments/delete-comment.md): Soft-deletes one comment. Only the author, or an ADMIN/OWNER, may delete it.

## OpenAPI Specs

- [openapi](https://api.galtea.ai/openapi.json)

## Optional

- [Blog](https://galtea.ai/blog)
- [Changelog](https://docs.galtea.ai/changelog)