# How Axari uses HiddenLayer

As published on [hiddenlayer.com](https://www.hiddenlayer.com/case-study/axari-ai-security-case-study), September 2026. Captured by usedby on 2026-10-06.

- Company: [Axari](https://www.usedby.ai/companies/axari.md)
- Tool: [HiddenLayer](https://www.usedby.ai/tools/hiddenlayer.md)

## What the story says

Axari, which builds an AI workforce platform for security teams, uses HiddenLayer's AI Runtime Security in production to monitor its agents' live flows. It detects prompt injection in ingested customer content, watches agent tool-call behavior during execution, and inspects outgoing content for sensitive data.

Summary written by usedby from the source page, in English. The figures are those of HiddenLayer and Axari, not ours.

> Axari now has production visibility into potential prompt-injection attempts originating from customer-provided content. The team can distinguish suspicious instructions embedded in external data from the system instructions Axari intentionally provides to Twin.

## What usedby checked

We compared the story with its live page on 2026-10-06.

- Checked: the passage quoted above is copied word for word from the page, near the name of Axari.
- Checked: the publication date is read from the page’s own metadata, never guessed.
- Checked: Axari uses HiddenLayer. Confirmed line. Latest check across sources: 2026-10-06.
- Not checked: the result itself. We quote it; we did not measure it.

---
Source: https://www.usedby.ai/case-studies/axari-hiddenlayer · How we check: https://www.usedby.ai/methodology