Arcjet launches in-code controls for AI agents taking real-world actions

David Mytton's third startup connects agent traces across sessions and can block tool, API and database calls before execution.

By · Published

Primary source: PR Newswire

Why it matters

AI agents can move money, expose data and alter production systems. Arcjet is betting that deterministic checks inside application code can control those actions before damage occurs.

Hands type on a keyboard in front of a monitor displaying code, with glowing digital effects showing agent actions being blocked.

In a September 17th announcement, David Mytton (@davidmytton) launched Arcjet's agent runtime security product, extending his code-first security thesis into production AI agents that can send email, issue refunds and modify databases.…

When you purchase through links in our articles, we may earn a small commission. This doesn’t affect our editorial independence.

Reader comments

Conversation for this story loads after sign-in.