SandboxAQ added two tools to its Switch AI platform on Monday, Oct. 19, to help companies check that their AI agents are safe and worth what they cost, TNW reported.[1] Switch Trust finds a company's AI agents, including ones security teams may not know about, and tests them against attacks such as prompt injection, where hidden instructions trick an agent into misbehaving.[1] Switch ROI tracks what each agent costs and links that spending to results, such as support tickets closed or tasks automated.[1] Both work with agents from any vendor and are free for up to five agents, according to a company blog post that did not list paid prices.[1] The launch comes as many companies struggle to get value from agents.[1]