For AI agents: a documentation index is available at the root level at /llms.txt. Append /llms.txt to any URL for a page-level index, or .md for the markdown version of any page.
LogoLogo
DiscordPlatform
DocumentationIntegrationsAPI referenceSDKsChangelog
DocumentationIntegrationsAPI referenceSDKsChangelog
    • Overview
    • Live demo
  • Get started
    • Start tracing
    • Setup evals
    • Use gateway
  • Observability
    • Users
  • Evaluations
    • Quickstart
    • Concepts
    • Experiments
    • Online evals
  • Prompt management
    • Quickstart
    • Structured output
    • Tool calling
    • Prompt composition
    • Advanced configurations
    • Playground
  • Gateway
    • Limits
  • Admin
    • API keys
    • Provider keys
    • Workspaces & projects
    • Collaborate
  • Resources
  • Security & Support
    • Support
    • Status
  • Overview
  • Live demo
  • MCP
  • CLI
  • Agent
  • Quickstart
  • Core concepts
  • Set up the SDK
  • Decorators (@workflow, @task)
  • Override span fields
  • Metadata & tags
  • Span types & multimodal
  • Manually log spans
  • Retention & export
  • Metrics & charts
  • Views & saved filters
  • Monitors & notifications
  • Users
  • Quickstart
  • Concepts
  • Overview
  • Building your first LLM eval
  • Deterministic code checks
  • Weighted-average scoring
  • Route failures to human review
  • Overview
  • Datasets for prompt optimization
  • Datasets for model comparison
  • Datasets for production data
  • Experiments
  • Online evals
  • Quickstart
  • Structured output
  • Tool calling
  • Prompt composition
  • Advanced configurations
  • Playground
  • Quickstart
  • Metadata
  • Models
  • Routing
  • Fallback
  • Load balancing
  • Retries
  • Respan caching
  • Prompt caching
  • Limits
  • API keys
  • Provider keys
  • Workspaces & projects
  • Collaborate
  • End-to-end: from first API call to production monitoring
  • Trace a RAG pipeline
  • Monitor an AI agent in production
  • Build an eval pipeline from production logs
  • A/B test prompts in production
  • Migrate from OpenAI to multi-model
  • Track cost per feature
  • GEPA: self-improving prompt optimization
  • How to structure LLM output with Anthropic models
  • Filters in Jinja templates
  • Trace CLI coding agents
  • Use Respan AI gateway as a proxy for coding agents
  • Span Attributes
  • Error handling
  • API rate limits
  • Architecture & encryption
  • Compliance & privacy
  • Support
  • Status
DiscordPlatform
On this page
  • Support
  • Resources
  • Connect
Security & Support

Support

Get help and connect with the Respan community

Support

Discord Community

Join our active community for real-time help and discussions

Email

Reach the team directly at team@respan.ai

Book a Demo

Schedule a personalized demo with our team

Resources

GitHub

Open source examples and contributions

YouTube

Tutorials and product updates

Blog

Latest features and insights

Changelog

Product updates and releases

Status Page

Real-time system status

Platform

Access your dashboard

Connect

LinkedIn

Follow our company updates

Twitter

Latest news and announcements


Was this page helpful?
Previous

Status

Real-time status of Respan services

Next
Built with