# Perplexity shares how it engineers safer agents

Perplexity says it has built safeguards into its infrastructure, harnesses, and tools and applied them across its products, and has published an account of that approach.

Language: en
Time zone: America/Los_Angeles
Current time (UTC, cached as of): 2026-10-24T14:00:00.000Z
Query date (America/Los_Angeles): 2026-10-24

HTML: https://didcodexreset.com/news/f047f47a3111481bbd82d0ff.html

Content language: en
Localization state: sameLanguage

Source: Perplexity · Published 9/29/2026, 08:17:37

Perplexity says agent governance is an engineering problem. It says it has built safeguards into its infrastructure, harnesses, and tools and put them to work across its products.

The account is published as [How we engineer safer agents](https://www.perplexity.ai/hub/blog/how-we-engineer-safer-agents).

Tags: Perplexity, AI agents, Agent safety, Safeguards

[View original post](https://x.com/perplexity_ai/status/2104952495147819431)