How to build a secure-by-default AI coding agent
Ryan interviews Greg Jennings, Anaconda’s VP of Engineering for AI Products, on building secure-by-default AI coding agents, the limits of relying on prompts as security controls, and how acquisitions help strengthen the AI software supply chain.
MAIN POINTS
- Secure-by-default design is essential for trustworthy AI coding agents.
- Prompts alone are not reliable security guardrails.
- Anaconda is using acquisitions to improve AI software supply chain security.
- The discussion centers on practical engineering and security tradeoffs in AI products.
TAKEAWAYS
- Security must be built into AI agents from the start, not added later.
- Natural-language prompts should guide behavior, not serve as enforcement mechanisms.
- Supply chain security is becoming a core concern in AI software ecosystems.
- Strategic acquisitions can accelerate security capabilities and platform trust.