More The AI Native Dev episodes

Cisco Principal Engineer's Fix for AI Code Security thumbnail

Cisco Principal Engineer's Fix for AI Code Security

Published 25 Feb 2026

Duration: 2050

Experts share strategies for successfully developing AI models by effectively managing context, security, and performance.

Episode Description

Your AI coding agent learned from millions of lines of code, including insecure ones. That means by default, it can write vulnerable code too. So how...

Overview

The discussion explores key challenges and best practices in AI development, with a particular focus on managing context to prevent AI models from becoming overwhelmed by excessive information. Effective strategies include segmenting large concepts into separate files and using cross-referencing to improve efficiency. The text also introduces CodeGuard, a security tool that helps prevent insecure coding by AI agents, demonstrating measurable improvements in secure development practices.

Further topics include the difficulties of ensuring AI agents adhere to security guidelines, the complexity of agent structures, and the integration of various tools. The importance of performance evaluations in enhancing AI capabilities is highlighted, along with the need to balance security requirements with budget constraints. The evolution of development tools and the necessity of structured, secure skill creation are also discussed, emphasizing the role of iterative evaluation processes in tracking AI performance improvements and maintaining consistent security across different coding environments.

Recent Episodes of The AI Native Dev

10 Nov 2026 Edith Harbaugh: Code Is Cheap. The Last Mile Isn't.

Feature flags and AI agents transform software delivery by enabling autonomous rollbacks and rapid iteration, though human judgment remains vital for defining success and maintaining stability.

27 Oct 2026 Caleb Sima: AI Attackers Move at Machine Speed

"AI-driven cybersecurity threats are evolving rapidly, with attackers leveraging speed, complexity, and swarm-like behavior to exploit vulnerabilities, necessitating advanced defensive strategies like automation and high-fidelity monitoring to counter escalating risks."

13 Oct 2026 Maria Gorinova: Feedback Loops That Fix Your Codebase

"Software factories and agentic coding require robust feedback loops to balance efficiency, reliability, and human oversight, with structured workflows and clear intent improving automation outcomes."

More The AI Native Dev episodes