· ai-devtools
AI agent API security hasn't caught up with agents already running in production
A quarter of the organizations surveyed already have agents making calls to their APIs while running in production.
This finding emerged from a survey administered by Postman to nearly 9,000 developers, architects, and executives regarding their management of AI agents.
The responses reveal a common pattern: enterprises prioritized deploying the new technology before establishing clear protocols for access control.
The complexities surrounding who controls the necessary keys present a significant challenge.
Specifically, roughly four out of every ten respondents mentioned they have not yet figured out how to manage credentials and identity for these agents.





