How Okta sets guardrails and context for AI agents

<p>In this episode of Engineering Enablement, Robert Lucero, Chief Architect at Okta, joins host Brian Houck to discuss how agentic AI is changing identity and access management. They explore how organizations should define agent identities, why authentication and authorization remain foundational, and how sandboxing, fine-grained permissions, and just-in-time access can enable agents to operate autonomously without creating unacceptable risk.</p><p>Robert shares what Okta has learned from driving AI adoption among security-minded engineers, what makes a repository ready for AI agents, and why strong testing, CI, and review processes matter even more as AI generates more code. They also discuss AI’s role in software validation, the need for human judgment, and whether AI will ultimately give the advantage to security teams or attackers.</p><p><br /></p><p><strong>Where to find Robert Lucero:</strong></p><p>• LinkedIn: <a href="https://www.linkedin.com/in/rlucero" rel="ugc noopener noreferrer" target="_blank">https://www.linkedin.com/in/rlucero</a> </p><p><br /></p><p><strong>Where to find Brian Houck: </strong></p><p>• LinkedIn: <a href="https://www.linkedin.com/in/brianhouck" target="_blank" rel="ugc noopener noreferrer">⁠⁠https://www.linkedin.com/in/brianhouck⁠⁠</a></p><p><br /></p><p><strong>In this episode, we cover:</strong></p><p>(00:00) Intro</p><p>(02:16) Meet Robert Lucero</p><p>(02:56) Why identity becomes critical as AI agents access more systems</p><p>(06:07) Governing automated access for non-deterministic agents</p><p>(08:01) Defining and managing agent identities</p><p>(10:32) Authentication and authorization for AI agents</p><p>(13:33) Determining how much autonomy to give AI agents</p><p>(19:44) Identity systems as the control plane for AI agents</p><p>(22:40) Driving AI adoption among security-minded engineers</p><p>(25:48) Why AI’s impact on engineering extends beyond coding</p><p>(28:44) The three components of AI readiness for repositories</p><p>(30:55) AI’s role in software testing and validation</p><p>(34:26) Whether AI gives defenders or attackers the advantage</p><p>(36:01) Where to find the best food in the country</p><p><br /></p><p><strong>Referenced:</strong></p><p>• <a href="https://getdx.com/report/State-of-AI-Impact-in-Engineering-Q2-Report" rel="ugc noopener noreferrer" target="_blank">State of AI Impact in Engineering Q2 Report 2026</a></p><p>• <a href="https://www.okta.com/" rel="ugc noopener noreferrer" target="_blank">Okta</a></p><p>• <a href="https://openai.com/index/hugging-face-incident-and-the-road-ahead/" rel="ugc noopener noreferrer" target="_blank">The Hugging Face incident and the road ahead | OpenAI</a></p><p>• <a href="https://github.com/features/copilot" rel="ugc noopener noreferrer" target="_blank">GitHub Copilot · Your AI pair programmer</a></p><p>• <a href="https://claude.com/product/claude-code" rel="ugc noopener noreferrer" target="_blank">Claude Code by Anthropic | AI Coding Agent, Terminal, IDE</a></p><p>• <a href="https://queue.acm.org/doi/10.1145/3807963" rel="ugc noopener noreferrer" target="_blank">Eight Myths on Software Engineering and GenAI | Queue</a></p><p>• <a href="https://www.linkedin.com/in/adriana-corona/" rel="ugc noopener noreferrer" target="_blank">Adriana Corona </a><br /></p>