# ZeroEval Documentation

## Docs

- [Introduction](https://docs.zeroeval.com/autotune/introduction.md): Version, track, and optimize every prompt your agent uses
- [Optimization](https://docs.zeroeval.com/autotune/prompts/optimization.md): Use feedback on production traces to generate and validate better prompts
- [API Reference](https://docs.zeroeval.com/autotune/reference.md): REST API for managing prompts, versions, and deployments
- [Python](https://docs.zeroeval.com/autotune/sdks/python.md): Track and version prompts in Python with ze.prompt()
- [TypeScript](https://docs.zeroeval.com/autotune/sdks/typescript.md): Track and version prompts in TypeScript with ze.prompt()
- [API Reference](https://docs.zeroeval.com/feedback/api-reference.md): REST API for submitting and retrieving feedback
- [Introduction](https://docs.zeroeval.com/feedback/human-feedback.md): Collect feedback from reviewers in the dashboard or from end users via the API
- [Introduction](https://docs.zeroeval.com/feedback/introduction.md): Attach human and AI feedback to your agent interactions to drive quality improvements
- [Python](https://docs.zeroeval.com/feedback/python.md): Submit completion feedback from Python to power prompt optimization
- [TypeScript](https://docs.zeroeval.com/feedback/typescript.md): Submit completion feedback from TypeScript to power prompt optimization
- [CLI](https://docs.zeroeval.com/integrations/cli.md): Manage traces, prompts, judges, and optimization from your terminal
- [Introduction](https://docs.zeroeval.com/integrations/introduction.md): Ways to integrate ZeroEval beyond the core SDKs
- [MCP](https://docs.zeroeval.com/integrations/mcp.md): Connect AI agents to ZeroEval via the Model Context Protocol
- [Skills](https://docs.zeroeval.com/integrations/skills.md): Set up ZeroEval from inside Cursor, Claude Code, Codex, and other coding agents
- [Calibration](https://docs.zeroeval.com/judges/calibration.md): Correct judge evaluations to improve accuracy over time
- [Introduction](https://docs.zeroeval.com/judges/introduction.md): AI evaluators that give automated feedback on your agent's interactions
- [Multimodal Evaluation](https://docs.zeroeval.com/judges/multimodal-evaluation.md): Evaluate screenshots and images with LLM judges
- [Pulling Evaluations](https://docs.zeroeval.com/judges/pull-evaluations.md): Retrieve judge evaluations via SDK or REST API
- [API Reference](https://docs.zeroeval.com/tracing/api-reference.md): REST API for ingesting and querying spans, traces, and sessions
- [Introduction](https://docs.zeroeval.com/tracing/introduction.md): Capture every step your AI agent takes so you can debug, evaluate, and optimize
- [OpenTelemetry](https://docs.zeroeval.com/tracing/opentelemetry.md): Send traces to ZeroEval via the OpenTelemetry Protocol (OTLP)
- [Integrations](https://docs.zeroeval.com/tracing/sdks/python/integrations.md): Automatic instrumentation for popular AI/ML frameworks
- [Reference](https://docs.zeroeval.com/tracing/sdks/python/reference.md): Complete API reference for the Python SDK
- [Setup](https://docs.zeroeval.com/tracing/sdks/python/setup.md): Get started with ZeroEval tracing in Python applications
- [Integrations](https://docs.zeroeval.com/tracing/sdks/typescript/integrations.md): Automatic tracing for popular AI/ML libraries
- [Reference](https://docs.zeroeval.com/tracing/sdks/typescript/reference.md): Complete API reference for the TypeScript SDK
- [Setup](https://docs.zeroeval.com/tracing/sdks/typescript/setup.md): Get started with ZeroEval tracing in TypeScript and JavaScript applications

## OpenAPI Specs

- [openapi](https://docs.zeroeval.com/api-reference/openapi.json)


Built with [Mintlify](https://mintlify.com).