AI agents

6 stories

Stories

Introducing Agent Runtime Security: Observe, Enforce, Audit
Which agents are running? Should this particular action be allowed? What happened, and why? This is what Arcjet is now tackling.
Arcjet BlogSep 17, 20265 min read
The two speeds of AI agent runtime security
AI agent security is moving at two speeds: most teams need action-level runtime enforcement now, while Google’s Beyond Zero points to what comes next.
Arcjet BlogJul 29, 20268 min read
Running PII detection locally with the Rampart NER model
How Arcjet added an optional on-device model backend for sensitive information detection: a pluggable rule interface, deterministic recognizers for structured data, offset reconstruction for token-classification output, and local ONNX inference in the request path.
Arcjet BlogJul 1, 202611 min read
Announcing advanced bot signals to detect automation without CAPTCHAs
Arcjet Signals are evaluated without a CAPTCHA and enforced when the request passes through a critical flow. The browser gives us signals. The application gives us intent.
Arcjet BlogJun 3, 20267 min read
Designing a CLI for AI agents
How we designed the Arcjet CLI in Go as a stable, defensive interface for humans and AI agents: predictable commands, machine-readable output, strict validation, and confirmation before production changes.
Arcjet BlogJun 2, 202611 min read
Unified skills, Python docs, email management
What's new in Arcjet (2026-05-22). Unified coding agent skills, expanded Python docs, email notification management.
Arcjet BlogMay 22, 20262 min read