# HoneyHive AI Docs > AI observability and evaluation platform. Trace, evaluate, monitor, and improve AI agents and LLM applications. ## Documentation - [HoneyHive Overview](https://docs.honeyhive.ai/v2/introduction/what-is-hhai.md): Getting started with HoneyHive ## Getting Started - [Tracing Quickstart](https://docs.honeyhive.ai/v2/introduction/tracing-quickstart.md): Trace your first AI application in 5 minutes - [Experiments Quickstart](https://docs.honeyhive.ai/v2/introduction/experiments-quickstart.md): Run your first experiment with HoneyHive in 5 minutes - [Use with Coding Agents](https://docs.honeyhive.ai/v2/introduction/ai-coding-agents.md): Give AI coding agents HoneyHive skills, CLI access, and live documentation context. - [Troubleshooting & FAQs](https://docs.honeyhive.ai/v2/introduction/troubleshooting.md): Common issues, solutions, and frequently asked questions ## Observability - [Introduction](https://docs.honeyhive.ai/v2/tracing/introduction.md): Getting started with tracing in HoneyHive. - [Concepts](https://docs.honeyhive.ai/v2/tracing/concepts.md): Core concepts behind HoneyHive's tracing data model, event schema, and OpenTelemetry architecture. - [Custom Spans](https://docs.honeyhive.ai/v2/tracing/custom-spans.md): Create custom spans for business logic tracing and workflow observability - [Tracer Initialization](https://docs.honeyhive.ai/v2/tracing/tracer-initialization.md): Where to initialize the tracer for scripts, evaluate(), Lambda, and web servers. - [Overview](https://docs.honeyhive.ai/v2/tracing/enrich-traces.md): Add custom attributes to your traces for filtering, debugging, and evaluation - [Schema Reference](https://docs.honeyhive.ai/v2/tracing/enrichment-schema.md): Complete reference for enrichment namespaces, data types, and backend attributes - [User Feedback](https://docs.honeyhive.ai/v2/tracing/setting-user-feedback.md): Capture user ratings, comments, and implicit signals on your traces - [Custom Metrics](https://docs.honeyhive.ai/v2/tracing/client-side-evals.md): Log evaluation scores and guardrail results computed in your application - [Configuration](https://docs.honeyhive.ai/v2/tracing/configuration-details.md): Log prompt templates, model parameters, and other configuration context on your traces - [User Properties](https://docs.honeyhive.ai/v2/tracing/setting-user-properties.md): Add user context to your traces for user-centric filtering and analysis - [Online Experiments](https://docs.honeyhive.ai/v2/tracing/online-experimentation.md): Tag traces with experiment IDs and variants to analyze A/B test results in HoneyHive - [Distributed Tracing](https://docs.honeyhive.ai/v2/tracing/distributed-tracing.md): How to trace application execution across multiple services. - [Multi-Instance Tracing](https://docs.honeyhive.ai/v2/tracing/multi-instance.md): Run multiple tracer instances for multi-tenant, A/B testing, or environment-based routing. - [Multi-Provider Tracing](https://docs.honeyhive.ai/v2/tracing/multi-provider.md): Trace applications that call more than one LLM provider in the same workflow. - [Multi-Modal Tracing](https://docs.honeyhive.ai/v2/tracing/multi-modal.md): Trace pipelines that process images, audio, video, and other media - [Multi-Threading (Python)](https://docs.honeyhive.ai/v2/tracing/multithreading.md): How to trace multi-threaded applications in Python with HoneyHive. - [Sampling](https://docs.honeyhive.ai/v2/tracing/sampling.md): Control which requests get traced in high-volume applications. - [Span Filtering](https://docs.honeyhive.ai/v2/tracing/filtering.md): Filter out noisy or unwanted spans from your traces using prefix-based rules. - [Tracing via API](https://docs.honeyhive.ai/v2/tracing/manual-instrumentation.md): Logging your application execution to HoneyHive without using the tracers - [Explore in UI](https://docs.honeyhive.ai/v2/tracing/ui-flows.md): Learn how to navigate, debug, and curate data from your traces in the Traces page - [Tree View](https://docs.honeyhive.ai/v2/tracing/tree-view.md): Inspect the hierarchical span tree showing parent-child relationships in your traces - [Timeline View](https://docs.honeyhive.ai/v2/tracing/timeline-view.md): Visualize span durations as a Gantt chart to identify latency bottlenecks - [Graph View](https://docs.honeyhive.ai/v2/tracing/graph-view.md): Visualize execution flow as a directed graph with latency bottlenecks and agent paths - [Trajectory View](https://docs.honeyhive.ai/v2/tracing/trajectory-view.md): Visualize agent behavior patterns as a bubble chart across execution steps - [Thread View](https://docs.honeyhive.ai/v2/tracing/thread-view.md): View conversational traces as a chronological message thread - [Session Aggregations](https://docs.honeyhive.ai/v2/tracing/aggregation-logic.md): Reserved session metadata fields that HoneyHive automatically calculates - [Export Data](https://docs.honeyhive.ai/v2/tracing/query-data.md): Programmatically query and export trace data from HoneyHive. - [Dashboard](https://docs.honeyhive.ai/v2/monitoring/overview.md): Analyze cost, latency, and quality metrics from your AI application in HoneyHive's monitoring dashboard. - [Custom Charts](https://docs.honeyhive.ai/v2/monitoring/charts.md): How to use HoneyHive's Discover interface to measure performance and discover interesting trends. - [Online Evaluations](https://docs.honeyhive.ai/v2/monitoring/onlineevals.md): Run evaluators automatically on ingested traces to continuously monitor quality. - [Overview](https://docs.honeyhive.ai/v2/monitoring/alerts/alerts_overview.md): Learn about HoneyHive alerts - types, states, and how they help you monitor LLM application performance. - [Creating Alerts](https://docs.honeyhive.ai/v2/monitoring/alerts/alerts.md): Step-by-step guide to creating alerts that monitor your AI application's performance, quality, and cost metrics. ## Evaluation - [Introduction](https://docs.honeyhive.ai/v2/evaluation/introduction.md): Systematically test and improve your AI applications with experiments - [Concepts](https://docs.honeyhive.ai/v2/evaluation/concepts.md): How experiments work in HoneyHive - [Comparing Experiments](https://docs.honeyhive.ai/v2/evaluation/comparing_evals.md): Compare experiment runs to identify improvements and regressions across prompts, models, or configurations. - [Experiments via API](https://docs.honeyhive.ai/v2/evaluation/via-api.md): Run experiments using the REST API for non-Python runtimes, custom pipelines, or CI systems - [CI Regression Detection](https://docs.honeyhive.ai/v2/evaluation/ci-regression-detection.md): Automatically catch quality regressions on every pull request using HoneyHive experiment comparison - [Introduction](https://docs.honeyhive.ai/v2/evaluators/introduction.md): An overview of HoneyHive evaluators - [Client-Side Evaluators](https://docs.honeyhive.ai/v2/evaluators/client_side.md): Run evaluation logic in your application code - [Python Evaluators](https://docs.honeyhive.ai/v2/evaluators/python.md): Create custom server-side evaluators using Python code to assess AI outputs - [LLM Evaluators](https://docs.honeyhive.ai/v2/evaluators/llm.md): Create LLM-powered evaluators to evaluate AI outputs using custom prompts - [Human Evaluators](https://docs.honeyhive.ai/v2/evaluators/human.md): Create human evaluator fields for manual review and annotation of AI outputs - [Composite Evaluators](https://docs.honeyhive.ai/v2/evaluators/composites.md): Combine multiple evaluators into a single aggregated score - [Version Control](https://docs.honeyhive.ai/v2/evaluators/versioning.md): Track changes and roll back evaluators to previous versions - [Evaluator Template List](https://docs.honeyhive.ai/v2/evaluators/evaluator-templates.md): A list of HoneyHive's server-side evaluator templates. - [Introduction](https://docs.honeyhive.ai/v2/datasets/introduction.md): An overview of HoneyHive datasets and their role in the AI application lifecycle. - [Curate from Traces](https://docs.honeyhive.ai/v2/datasets/dataset-curation.md): Build datasets from production traces in HoneyHive - [Upload Datasets](https://docs.honeyhive.ai/v2/datasets/import.md): How to upload datasets to HoneyHive via UI or SDK - [Sync from External Sources](https://docs.honeyhive.ai/v2/datasets/sync.md): Keep a HoneyHive dataset synced with S3, databases, or other external sources - [Export Datasets](https://docs.honeyhive.ai/v2/datasets/export.md): Programmatically export datasets from HoneyHive - [Import from Hugging Face](https://docs.honeyhive.ai/v2/datasets/hf-datasets.md): Import datasets from Hugging Face Datasets to HoneyHive - [Annotation Queues](https://docs.honeyhive.ai/v2/evaluation/annotation-queues.md): Learn how to create and manage annotation queues for human review and labeling. ## Prompt Management - [Managing Prompts](https://docs.honeyhive.ai/v2/prompts/overview.md): Create, test, and manage prompts in the HoneyHive Playground. - [Using Prompts in Code](https://docs.honeyhive.ai/v2/prompts/deploy.md): Fetch deployed prompts from HoneyHive and use them in your application. ## Administration - [Organization Hierarchy](https://docs.honeyhive.ai/v2/workspace/organization-hierarchy.md): How organizations, workspaces, and projects structure your HoneyHive account. - [Managing Projects](https://docs.honeyhive.ai/v2/workspace/projects.md): How to organize projects in HoneyHive for your AI applications. - [Inviting Teammates](https://docs.honeyhive.ai/v2/workspace/inviting-teammates.md): How to invite teammates to your HoneyHive organization, workspaces, and projects. - [Role Based Access Control](https://docs.honeyhive.ai/v2/workspace/roles.md): Manage user permissions across your organization, workspaces, and projects. - [Provider Keys](https://docs.honeyhive.ai/v2/workspace/provider-keys.md): Configure AI provider API keys for LLM evaluators and the Playground. - [Templates](https://docs.honeyhive.ai/v2/workspace/templates.md): Configure standard evaluators and monitoring charts across every project. - [Usage](https://docs.honeyhive.ai/v2/workspace/usage.md): View event counts, enrichment metrics, and export usage reports from Organization Settings. - [Multi-Tenant SaaS](https://docs.honeyhive.ai/v2/setup/managed.md): Getting started on HoneyHive's multi-tenant SaaS cloud. - [Dedicated Cloud](https://docs.honeyhive.ai/v2/setup/dedicated.md): Getting started on HoneyHive's dedicated cloud with isolated infrastructure. - [Self-Hosting Overview](https://docs.honeyhive.ai/v2/setup/self-hosted.md): Deploy HoneyHive in your private cloud or on-premise environment. - [Security Architecture](https://docs.honeyhive.ai/v2/setup/self-hosted/security.md): Security controls, encryption, and compliance for HoneyHive self-hosted deployments - [Data Flow & Residency](https://docs.honeyhive.ai/v2/setup/self-hosted/data-flow.md): Data classification, flow boundaries, and residency controls for HoneyHive self-hosted deployments - [Operations Guide](https://docs.honeyhive.ai/v2/setup/self-hosted/operations.md): Day 2 operations: upgrades, monitoring, backup, scaling, and incident response for self-hosted HoneyHive - [Infrastructure Requirements](https://docs.honeyhive.ai/v2/setup/infrastructure-requirements.md): Supported dependency versions for self-hosted HoneyHive deployments. - [Platform Architecture](https://docs.honeyhive.ai/v2/platform-architecture.md): How HoneyHive's Management Plane and Data Plane architecture works. - [Security](https://docs.honeyhive.ai/v2/setup/security.md): How HoneyHive protects your data, infrastructure, and AI applications. ## Learn More - [Overview](https://docs.honeyhive.ai/v2/concepts.md): The key concepts behind the HoneyHive Platform - [End-to-End: Multi-Agent Tracing and Evaluation](https://docs.honeyhive.ai/v2/tutorials/multi-agent-cookbook.md): Build a multi-agent customer support bot with Google ADK, add HoneyHive observability, and evaluate agent quality - [Add Tracing to Existing Apps](https://docs.honeyhive.ai/v2/tutorials/add-tracing-5min.md): Add HoneyHive tracing to your existing LLM application with just 5 lines of code - [Enrich Your Traces](https://docs.honeyhive.ai/v2/tutorials/enriching-traces.md): Add user IDs and custom metadata to make traces more useful - [Deploy Tracing to Production](https://docs.honeyhive.ai/v2/tutorials/production-deployment.md): Configure HoneyHive tracing for production environments - [Trace Distributed Systems](https://docs.honeyhive.ai/v2/tutorials/distributed-tracing.md): Trace requests across service boundaries with context propagation ## Reference - [SDK Overview](https://docs.honeyhive.ai/v2/sdk-reference/overview.md): Choose the right HoneyHive SDK for your use case ## Python SDK - [Python SDK](https://docs.honeyhive.ai/v2/sdk-reference/python-sdk-ref.md): Full-featured Python SDK built on OpenTelemetry - [Environment Variables](https://docs.honeyhive.ai/v2/sdk-reference/environment-variables.md): Configuration reference for HoneyHive Python SDK environment variables ## TypeScript API SDK - [TypeScript API SDK](https://docs.honeyhive.ai/v2/sdk-reference/typescript-sdk-ref.md): Type-safe TypeScript client for the HoneyHive REST API ## Semantic Conventions - [Semantic Convention Reference](https://docs.honeyhive.ai/v2/sdk-reference/semconv-reference.md): Canonical HoneyHive attribute names, special attribute behaviors, and UI sideview rendering reference - [Framework Attribute Mapping](https://docs.honeyhive.ai/v2/sdk-reference/semconv-alignment.md): How attributes from OTel GenAI, OpenInference, and Traceloop map to HoneyHive canonical schema keys ## CLI - [HoneyHive CLI](https://docs.honeyhive.ai/v2/sdk-reference/cli.md): Use the HoneyHive CLI to work with HoneyHive from your terminal ## OpenAPI Client - [OpenAPI Client (Any Language)](https://docs.honeyhive.ai/v2/sdk-reference/openapi-sdks.md): Generate lightweight API clients in any language using HoneyHive's public OpenAPI spec ## API Reference - [API Reference (OpenAPI spec)](https://raw.githubusercontent.com/honeyhiveai/honeyhive-openapi/main/openapi.yaml): Machine-readable OpenAPI 3.0 spec for the HoneyHive REST API. ## Agent Frameworks - [Claude Agent SDK](https://docs.honeyhive.ai/v2/integrations/claude-agent-sdk.md): Add HoneyHive observability to your Claude Agent SDK applications - [Cursor SDK](https://docs.honeyhive.ai/v2/integrations/cursor-sdk.md): Trace Cursor SDK agent runs in HoneyHive - [OpenAI Agents SDK](https://docs.honeyhive.ai/v2/integrations/openai-agents.md): Add HoneyHive observability to your OpenAI Agents SDK applications - [CrewAI](https://docs.honeyhive.ai/v2/integrations/crewai.md): Add HoneyHive observability to your CrewAI applications - [Google ADK](https://docs.honeyhive.ai/v2/integrations/google-adk.md): Add HoneyHive observability to your Google Agent Development Kit applications - [Pydantic AI](https://docs.honeyhive.ai/v2/integrations/pydantic-ai.md): Add HoneyHive observability to your PydanticAI agent applications - [Microsoft Semantic Kernel](https://docs.honeyhive.ai/v2/integrations/semantic-kernel.md): Add HoneyHive observability to your Semantic Kernel applications - [AWS Strands Agents](https://docs.honeyhive.ai/v2/integrations/strands.md): Add HoneyHive observability to your Strands Agents applications - [AutoGen](https://docs.honeyhive.ai/v2/integrations/autogen.md): Add HoneyHive observability to your AutoGen AgentChat applications - [LangChain](https://docs.honeyhive.ai/v2/integrations/langchain.md): Add HoneyHive observability to your LangChain applications - [LangGraph](https://docs.honeyhive.ai/v2/integrations/langgraph.md): Add HoneyHive observability to your LangGraph state graphs and workflows - [DSPy](https://docs.honeyhive.ai/v2/integrations/dspy.md): Add HoneyHive observability to your DSPy applications ## Model Providers - [Anthropic](https://docs.honeyhive.ai/v2/integrations/anthropic.md): Add HoneyHive observability to your Anthropic Claude applications - [OpenAI](https://docs.honeyhive.ai/v2/integrations/openai.md): Add HoneyHive observability to your OpenAI applications - [Azure OpenAI](https://docs.honeyhive.ai/v2/integrations/azure_openai.md): Add HoneyHive observability to your Azure OpenAI applications - [AWS Bedrock](https://docs.honeyhive.ai/v2/integrations/aws_bedrock.md): Add HoneyHive observability to your AWS Bedrock applications - [Gemini](https://docs.honeyhive.ai/v2/integrations/gemini.md): Add HoneyHive observability to your Google Gemini applications - [LiteLLM](https://docs.honeyhive.ai/v2/integrations/litellm.md): Add HoneyHive observability to your LiteLLM applications ## Coding Agents - [Claude Code](https://docs.honeyhive.ai/v2/integrations/claude-code.md): Export Claude Code sessions into HoneyHive for observability and evaluation ## Changelog - [Product](https://docs.honeyhive.ai/v2/changelog/product.md): New updates and improvements to our core platform and UI. - [Self-Hosting](https://docs.honeyhive.ai/v2/changelog/self-hosting.md): Updates to HoneyHive Helm charts for self-hosted deployments. ## SDK Changelogs - [Python SDK](https://docs.honeyhive.ai/v2/changelog/python-sdk.md)