#agentic systems

A security AI model maturity checklist and Sublime's four pillars of AI safety for agents that operate directly on attacker-authored content.

Four engineering pillars, a maturity checklist, and the concrete artifacts, gates, and numbers behind Sublime's AI safety program.

A real-world phishing campaign carrying an adversarial prompt injection payload against AI-based email security — and how ASA caught it.

A two-tier router architecture — fine-tuned open-weight model with uncertainty-based escalation to a frontier model — that cut ASA's median latency 16x and inference cost ~70% with no accuracy loss.

Guest segment on evaluating agentic AI in security, and how organizations are cutting through 'AI fatigue' to make real decisions about deployment.

Architectural deep-dive on tool scoping, platform-enforced authorization, prompt injection mitigation, and graduated oversight for production LLM agents.

How we architected ASA and ADÉ for adversarial production.