---
title: "Observe and troubleshoot | Grafana Cloud documentation"
description: "Inspect conversations, compare agents, and investigate performance and costs."
---

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

# Observe and troubleshoot

Use analytics to review activity across your agents, then explore agents and individual conversations to investigate what happened.

1. [Monitor agents with analytics](https://grafana.com/docs/grafana-cloud/observe-and-act/agent-observability/observe-and-troubleshoot/dashboards) to monitor activity, performance, quality, and cost.
2. [Monitor coding agents](https://grafana.com/docs/grafana-cloud/observe-and-act/agent-observability/observe-and-troubleshoot/coding-agents) to track usage, cost, tokens, and tools across coding agents.
3. [Use the agent catalog](https://grafana.com/docs/grafana-cloud/observe-and-act/agent-observability/observe-and-troubleshoot/agent-catalog) to review agents, versions, and prompt changes.
4. [Browse and debug conversations](https://grafana.com/docs/grafana-cloud/observe-and-act/agent-observability/observe-and-troubleshoot/conversations) to inspect responses, tool calls, failures, and linked traces.
5. [Optimize cost and performance](https://grafana.com/docs/grafana-cloud/observe-and-act/agent-observability/observe-and-troubleshoot/cost-optimization) to investigate usage and efficiency.
6. [Configure your model prices](https://grafana.com/docs/grafana-cloud/observe-and-act/agent-observability/observe-and-troubleshoot/model-prices) to investigate costs with the prices you pay.

When you find examples you want to test again, refer to [Evaluate and improve](https://grafana.com/docs/grafana-cloud/observe-and-act/agent-observability/evaluate-and-improve).

- [Monitor agents with analytics](https://grafana.com/docs/grafana-cloud/observe-and-act/agent-observability/observe-and-troubleshoot/dashboards/)  
  Monitor agent activity, performance, cost, and quality using the Agent Observability analytics dashboards.
- [Use the agent catalog](https://grafana.com/docs/grafana-cloud/observe-and-act/agent-observability/observe-and-troubleshoot/agent-catalog/)  
  Monitor agent versions, track tool and prompt changes, and compare performance across agents in the Agent Observability agent catalog.
- [Browse and debug conversations](https://grafana.com/docs/grafana-cloud/observe-and-act/agent-observability/observe-and-troubleshoot/conversations/)  
  Search, filter, and drill into conversations to understand what your agents did, where they failed, and how they performed.
- [Optimize cost and performance](https://grafana.com/docs/grafana-cloud/observe-and-act/agent-observability/observe-and-troubleshoot/cost-optimization/)  
  Use Agent Observability data to reduce LLM costs, improve cache efficiency, and tune agent performance.
- [Configure your model prices](https://grafana.com/docs/grafana-cloud/observe-and-act/agent-observability/observe-and-troubleshoot/model-prices/)  
  Set the prices you pay for LLM models so Agent Observability cost figures match your contract.
- [Monitor coding agents](https://grafana.com/docs/grafana-cloud/observe-and-act/agent-observability/observe-and-troubleshoot/coding-agents/)  
  See usage, cost, tokens, and tools across Claude Code, Cursor, Codex, and every other coding agent your team runs.

## Next steps

- [Evaluate and improve agent quality](https://grafana.com/docs/grafana-cloud/observe-and-act/agent-observability/evaluate-and-improve)
- [Add deeper instrumentation](https://grafana.com/docs/grafana-cloud/observe-and-act/agent-observability/instrumentation)