Aron Eidelman
Security Advocate
Santa Clara, California, United States
Actions
Aron Eidelman is a Senior Developer Relations Engineer focused on Security Advocacy at Google. Specializing in DevSecOps, AI runtime controls, and applying Site Reliability Engineering (SRE) to cybersecurity, he helps organizations build resilient, proactive defenses. A hands-on practitioner, Aron has demoed cloud and security innovations at major conferences, including RSAC, Next, and Google I/O.
Links
Area of Expertise
Topics
Red, Green, Refactor, Secure: The New Loop for Building with Agents
What if I told you that agents can produce secure, stable software?
According to the 2025 DORA report, AI-driven development is increasing throughput, but also increasing instability. In fact, a major blocker to adoption concerns security and quality issues. The result is often "slop," increased technical debt, and out-of-control batch sizes (like single commits with 1,802 deletions) that bypass review and break builds. In the worst cases, agents have deleted or leaked codebases.
This talk demonstrates how to mend that instability without killing the speed of agentic coding. We will move beyond basic Context Engineering using a single file to applying DORA best practices and security policies before a single line of code is written. You will learn how to enforce a strict Red/Green/Refactor loop that gets coding agents to work in small, known-good increments rather than generating massive, untestable blobs. Then you'll see how to add security as early as possible to mitigate the majority of issues before a team needs to worry.
Finally, we will show "shifting left" with agents using tools like security extensions and automated checkpoints to catch issues such as injection vulnerabilities, misconfigured IaC files, and business logic issues before they even commit to your repo.
You will leave this talk able to build software with an agent that follows test-driven development, extreme programming, and proactive application security.
Keep Secrets Secret: Automated PII Redaction for Gen AI & MCP
In the world of Gen AI and the Model Context Protocol (MCP), "Context" is King — but it’s also a liability. To debug complex agents, we log everything: prompts, tool outputs, and reasoning steps. The problem? That data is often radioactive with PII, API keys, and customer secrets.
In this session, we will explore the hidden compliance nightmare of AI observability. We’ll move beyond fragile Regex filters and demonstrate the architectural pattern of "AI-Empowered Sanitization". We will discuss how to use intelligent detection layers to identify sensitive entities in flight and redact them before they hit your logs. You’ll leave with a blueprint for a "Zero-Trust Logging" pipeline that keeps your debug streams useful but compliant.
Please note that Sessionize is not responsible for the accuracy or validity of the data provided by speakers. If you suspect this profile to be fake or spam, please let us know.
Jump to top