Cyber Security

Threat models, incident write-ups and the judgment calls automation cannot make.

3 stories

The Analyst Stays in the Loop

AI agents can close most alerts faster than any SOC shift. Deciding what an alert means for the business, and owning that call, is still a human job.

1w ago7 min read#security#soc#ai

Human StuffinCyber Security

Threat Modeling Is a Design Conversation

Threat modeling works best as a structured argument between the people building a system. A worked password-reset example, with STRIDE and the four questions.

1w ago7 min read#security#threat-modeling#appsec

Human StuffinCyber Security

Securing AI Agents in Production

Once an LLM can call tools, prompt injection stops being a chatbot quirk and becomes a path to your data. Practical controls, and where human review is mandatory.

2w ago6 min read#security#ai#llm

You’re all caught up.

Something on your mind? Write it down, or show me something amazing.