AI agents for security
AI Agents and Tool Use: How a Model Calls Functions
How tool use works: a model returns a structured call, your host program runs the tool, and approval rules decide what is allowed.
Agents that run security tools, how to set them up and how to check their work.
AI agents for security
How tool use works: a model returns a structured call, your host program runs the tool, and approval rules decide what is allowed.
AI agents for security
MCP is the open protocol that connects AI apps to tools and data. Learn its roles, primitives, transports and security model with a sandboxed lab.
Create an account, add credits from $10 and ask the first question in the chat or the terminal.
Individual or company. You can switch to a company later without losing balance or keys.
By card, from $10. Pay per token, no subscription.
In the chat, or install the CLI and run notholy login in your terminal.