OWASP LA October [VIRTUAL] Meetup Santiago Castiñeira

​TOPIC: The hardest problems we solved building AI agents for security

​ABSTRACT: Have you ever looked at how security gets done and thought, "I know AI could do this better"? Yeah, us too.

​Santiago Castiñeira, CTO and co-founder, digs into some of the most interesting, and hardest, problems his team solved between a working MVP and a system that runs across millions of vulnerabilities weekly:

• ​Building an accurate context layer that feeds the agents

• ​Understanding the difference between using one big prompt vs many specialized ones

• ​Selecting the best model for the job

• ​Designing an architecture that balances accuracy, efficiency, and cost

​It took over a year, and a lot of engineering creativity, to achieve results that are scalable, accurate, consistent, and won't break the bank. Come hear about what they learned.

​Sponsor: Maze

​SPEAKER BIO: Santiago Castiñeira is the Co-Founder and CTO of Maze, the agentic reasoning platform for vulnerability management. He brings years of hands-on experience in the field and spent 15+ years building and scaling software in senior technical roles at Amazon, S&P Global, Monad Inc, and Jungle Robotics. He pairs deep engineering expertise with a track record of turning complex security challenges into products teams can use.

​CODE OF CONDUCT

​OWASP is committed to providing a welcoming and inclusive environment for everyone. Please review the OWASP Conference and Event Anti-Harassment Policy:
https://owasp.org/www-policy/operational/conferences-events.html#conference-and-event-anti-harassment-policy

​Sponsorship Opportunities

​Sponsorship opportunities are available for future OWASP Los Angeles events. Vendors interested in sponsoring may contact:
sponsorship.la@owasp.org