Core AI Concepts
AI agent
An AI agent is a model given tools and autonomy — it browses, runs code, edits files, and takes multi-step actions, expanding both capability and blast radius.
An AI agent goes beyond answering: it plans and executes multi-step tasks using tools — browsing, code execution, file access, API calls. Agentic modes in coding tools, deep-research features, and workflow assistants are all agents in this sense.
Agency multiplies data exposure. An agent granted repository or inbox access reads far more than a human would paste, and prompt injection becomes an action risk rather than a content risk: malicious text can now trigger tool calls. Least-privilege access and action review are the emerging controls.
Where this shows up
Related terms
See it in your own organization.
Sanitized AI inventories the AI tools in use and redacts sensitive data from prompts before it leaves.