> For the complete documentation index, see [llms.txt](https://developer.harness.io/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://developer.harness.io/resilience-testing/3.0/shared-capabilities/ai/prompt-library.md).

# Prompt library

This page is a curated library of natural-language prompts for the Harness MCP server's resilience-testing toolset. Each card represents a real SRE scenario, mapped to specific Harness chaos resource types. Click any card to open the full prompt, fill in your service and tolerance values, and copy a ready-to-paste prompt for Cursor, Claude Desktop, Windsurf, or any other MCP-compatible AI client.

### Browse the prompts <a href="#browse-the-prompts" id="browse-the-prompts"></a>

#### Resilience coverage map <a href="#resilience-coverage-map" id="resilience-coverage-map"></a>

#### Fault catalog exploration <a href="#fault-catalog-exploration" id="fault-catalog-exploration"></a>

#### Service resilience risk scan <a href="#service-resilience-risk-scan" id="service-resilience-risk-scan"></a>

#### Pod failure experiment design <a href="#pod-failure-experiment-design" id="pod-failure-experiment-design"></a>

### Related concepts <a href="#related-concepts" id="related-concepts"></a>

* Go to [Resilience Testing MCP Tools](/resilience-testing/shared-capabilities/ai/mcp.md) to install and configure the Harness MCP server in your AI client.
* Go to [AI Reliability Agent](/resilience-testing/shared-capabilities/ai/ai-reliability-agent.md) to learn how Harness recommends and remediates experiments automatically.
* Go to [Pod Network Latency](/resilience-testing/chaos-engineering/faults/chaos-fault-categories/kubernetes/pod/pod-network-latency.md) to review the underlying network-latency fault and its tunables.