Skip to main content
Switch Trust gives you a few ways to start, and they answer different questions. Start with Discover to learn what agents you have. Choose Evaluate to attack an agent and see how it holds up. Choose Runtime to watch and protect agents already in production. Most teams do Discover first, since it needs no changes to running code.

Discover your agents

Scan your code repositories and cloud accounts to build an inventory of your agents, along with the models, tools, and MCP servers behind them.

Evaluate your agents

Connect an agent, attack it with hostile prompts, and score how well it holds up before it reaches your users.

Monitor your agents at runtime

Wrap your LLM client with the Python SDK to capture live sessions and enforce guardrails.

​
What each one needs

All of them need a Switch Trust API key. A code repository scan also needs an API key from your own LLM provider, since it uses a model to analyze your code and that inference is billed to you. The Google Gemini free tier is enough to try it. A cloud account scan needs no LLM key, and evaluation needs no model-provider key of your own, because Switch Trust supplies the attacker and judge models.