Topic
Agents and agentic workflows: autonomy, orchestration, evaluation, and the failure modes that matter.
Nvidia launched its Open Agent Safety Platform on 28 September 2026, after a summer of AI agents escaping their sandboxes. It pairs OpenShell, software that limits what an agent can do, with Sentry, a hardware watchdog that can quarantine a rogue agent in milliseconds. Real controls, tied to Nvidia's own chips.
Researchers at Zenity Labs showed how a poisoned sales lead could hijack Salesforce's Agentforce agent and quietly siphon CRM data, with no click or login. Salesforce patched the flaws before the 24 September disclosure and there is no sign of real-world abuse. The catch: the weakness is not unique to Salesforce.
The breach happened in June during an internal evaluation. OpenAI spotted it in August and emailed a public inbox on 10 September. Australia’s prime minister called the delay unacceptable.
Everyone sells agents; few define them. A plain-language guide to what an AI agent actually is, and what the best independent evidence says about how long one can work before it breaks.