Topic

Security

6 articles on Security, written from production systems rather than documentation.

3 min read

Testing an AI feature the way someone would attack it

Normal testing asks whether the system works for people trying to use it. Adversarial testing asks what happens when somebody is trying to make it fail.

AISecurityEvaluationAgents
Read post
4 min read

Choosing an MCP transport: stdio, HTTP, or neither yet

Stdio is the default and it quietly decides your deployment model. The transport question is really a question about process lifetime and blast radius.

AIMCPArchitectureSecurity
Read post
3 min read

Content moderation for a feature that generates text

Moderating what users send is the familiar half. Moderating what your own product says, in your name, is the half that carries the liability.

AISecurityEvaluationSystem Design
Read post
4 min read

Where personal data ends up in an LLM system

Prompts, traces, embeddings and evaluation sets all quietly become copies of user data, and most of them were never on anybody's data map.

AISecurityObservabilityArchitecture
Read post
3 min read

Prompt injection is an architecture problem

Instructions and data arrive in the same channel, so the model cannot tell them apart. No wording fixes that, because it is a property of the design.

AISecurityAgentsArchitecture
Read post
4 min read

What you are exposing when you add an MCP server

An MCP server turns an internal API into something a model calls on its own initiative. The threat model changes, and the existing auth boundary rarely fits.

AIMCPSecurityArchitecture
Read post

Have a system to build?

Whether it needs designing from scratch or rescuing from its own success, tell me what you’re building and I’ll tell you how I’d architect it.

Open to remote and hybrid work worldwide