Datadog CISO on Securing AI Agents at Scale | Deep Dives with a16z

影片總結

Datadog CISO Emilio Escobar explains how 4,000 engineers use AI agents, while role-based MCP servers and an LLM judge help catch malicious code.

Datadog CISO Emilio Escobar tells a16z’s Joel De La Garza that Datadog moved from 50 Cursor licenses to AI adoption across nearly every employee, including more than 4,000 engineers. Rather than block tools, the company governs access: role-based MCP servers limit which business data employees can query, while sandboxing keeps agents away from stored credentials and provides short-lived tokens when needed. Datadog also built an LLM-based “judge” to assess code and AI skills for malicious intent, after finding harmful skills in marketplaces and detecting injected code in compromised packages. Escobar warns that agents can misuse permissions or “fix” a problem by disabling a database. He is less concerned about AI escaping sandboxes than the surge in vulnerabilities, weak processes for prioritizing them, and exaggerated trust in model-generated findings. His prescription: build security with engineers and avoid gatekeeping.

章節

1. 0:00Deploying AI at Datadog: From 50 Cursor Licenses to Other Coding Agents
2. 3:11AI Flattens the Org: 4,000 Engineers and a Sales Rep Querying Enterprise Data
3. 5:19Role-Based MCP Servers and Sandboxing Agent Credentials at Datadog
4. 7:34The Intent Judge: Datadog's LLM Catches Malicious Code and Agent Skills
5. 10:27Reward Hacking: Datadog Checks Agents That Might Fix 4 a.m. Paging by Turning Off a Database
6. 12:07The Helplessness Problem: CISOs Can Empower Developers Instead of Waiting for Vendors
7. 14:05Security Engineers Will Become Real Engineers: Pay Parity, DevEx Collaboration, and Less Scanner Noise
8. 18:12“AI Has Gone Wild”: Emilio Escobar on Access Rules, Vulnerability Volume, and Model Findings

完整分析還有什麼

8 章 · 40 個重點 · 8 段段落總結 · 心智圖

其餘 37 個重點、段落總結與心智圖在完整分析裡。 分析這支影片,看完整內容 →