---
title: "Guides | Grafana Cloud documentation"
description: "Practical workflows for instrumenting agents, debugging conversations, evaluating quality, and optimizing costs with Agent Observability."
---

> For a curated documentation index, see [llms.txt](/llms.txt). For the complete documentation index, see [llms-full.txt](/llms-full.txt).

# Guides

Explore practical workflows for getting the most out of Agent Observability.

- [Browse and debug conversations](/docs/grafana-cloud/observe-and-act/agent-observability/guides/conversations/)  
  Search, filter, and drill into conversations to understand what your agents did, where they failed, and how they performed.
- [Instrument agent dependencies and workflows](/docs/grafana-cloud/observe-and-act/agent-observability/guides/agent-dependencies-and-workflows/)  
  Learn when to use generation dependencies, workflow steps, or both to visualize and debug agent execution in Agent Observability.
- [Instrument agents with frameworks](/docs/grafana-cloud/observe-and-act/agent-observability/guides/instrument-agents/)  
  Use Agent Observability framework integrations to automatically capture generations from LangChain, LangGraph, OpenAI Agents, Vercel AI SDK, and other frameworks.
- [Use the agent catalog](/docs/grafana-cloud/observe-and-act/agent-observability/guides/agent-catalog/)  
  Monitor agent versions, track tool and prompt changes, and compare performance across agents in the Agent Observability agent catalog.
- [Use built-in dashboards](/docs/grafana-cloud/observe-and-act/agent-observability/guides/dashboards/)  
  Monitor agent activity, performance, cost, and quality using the Agent Observability analytics dashboards.
- [Set up online evaluation](/docs/grafana-cloud/observe-and-act/agent-observability/guides/evaluation/)  
  Create evaluators to continuously score agent quality on live production traffic.
- [Optimize cost and performance](/docs/grafana-cloud/observe-and-act/agent-observability/guides/cost-optimization/)  
  Use Agent Observability data to reduce LLM costs, improve cache efficiency, and tune agent performance.
- [Set up guards](/docs/grafana-cloud/observe-and-act/agent-observability/guides/guards/)  
  Configure guards to block, redact, or filter LLM requests before they reach the model.
- [Instrument coding agents](/docs/grafana-cloud/observe-and-act/agent-observability/guides/instrument-coding-agents/)  
  Forward coding-agent sessions to Agent Observability without writing SDK code.
- [Migrate from sigil-sdk to agento11y](/docs/grafana-cloud/observe-and-act/agent-observability/guides/migrate-sigil-sdk-to-agento11y/)  
  Update Agent Observability SDK packages, imports, environment variables, telemetry names, and Grafana app permissions from sigil-sdk to agento11y.
- [Experiments](/docs/grafana-cloud/observe-and-act/agent-observability/guides/experiments/)  
  Learn how experiments connect production conversations, test suites, agent evaluations, and delivery workflows in Grafana Agent Observability.