Box Solutions Engineer Hébrard: The Bottleneck for AI Agents Is Not the Model, It's Content
In a discussion co-hosted by Sifted and Box, four AI practitioners identified the core constraints to scaling autonomous agent security from different angles: content quality, zero-trust assumptions, progressive authorization, and clear human oversight responsibilities, rather than model capability itself.
As enterprises shift from AI copilots to autonomous agents, a constraint that is often underestimated is the data the agents access themselves. Eléonore Hébrard, a solutions engineer at Box, offered a concise assessment during a discussion jointly hosted by Sifted and Box: agents can hallucinate and fail when fed disorganized data or encountering duplicate or outdated files—the problem lies not with the AI, but with the content. She further noted that an agent's speed and capacity make the blast radius of errors far greater than human operational mistakes; therefore, data governance is not optional but a prerequisite.
Leo Rosales, co-founder and CTO of Ralio, approached the issue from another angle: maintaining skepticism toward third-party AI models themselves. He described his company's approach as assuming the model has been compromised and building control layers around that assumption. They define what an agent can and cannot do, directly blocking it when it attempts to execute actions beyond its authorized scope. This is not a localized validation of model output, but a fundamental distrust of the entire model's reliability—here, 'zero trust' means a default hostile assumption toward the model itself.
Mick McNeil, founder and CEO of Deliverance AI, compared agent deployment to new employee onboarding. He would not grant a new salesperson full access to all company systems on day one; instead, he defines their role scope, gradually opens system access, and has managers continuously monitor performance. An agent's autonomy should be earned over time, not granted in one lump sum. He emphasized that while giving agents knowledge, you must also provide context—just as you define role boundaries for humans, you must instruct the agent on how to think and act when it encounters data.