Category archive

Evaluation and security are one discipline aimed at two failures.

Both questions are the same question asked twice: what does this system do when its input is wrong, and what does it do when its input is hostile. An evaluation harness that cannot block a release and a guardrail that only blocks keywords fail for the same reason, so they belong in one archive.

7 articlesEvaluation and Security

Articles in Evaluation and Security

Evaluation and SecurityJul 9, 202613 min read
Synthetic Evaluation Data That Finds Real Failures
How to generate, filter, diversify, and maintain synthetic cases without turning an evaluation suite into a mirror of its generator.
Evaluation and SecurityJul 3, 202613 min read
Privacy-Preserving AI Is a Dataflow Architecture
Purpose limitation, minimization, isolation, retention, redaction, and verifiable deletion across retrieval, models, tools, traces, and feedback loops.
Evaluation and SecurityMay 18, 202610 min read
Build an LLM Evaluation Harness That Can Block a Release
From task contracts and test slices to calibrated judges, regression budgets, and production feedback loops.
Evaluation and SecurityMay 9, 202611 min read
Hallucination Controls Belong in the System, Not One Prompt
A layered design for constraining claims, grounding evidence, verifying outputs, and abstaining when the system does not know.
Evaluation and SecurityApr 30, 202610 min read
Guardrails as Policy Enforcement, Not Keyword Blocking
Building layered input, action, and output controls that remain testable when language and threats change.
Evaluation and SecurityApr 21, 202610 min read
Threat Modeling an AI Application End to End
Assets, trust boundaries, model-specific attacks, tool abuse, data leakage, and concrete mitigations for deployed AI systems.
Evaluation and SecurityApr 12, 202614 min read
Prompt Injection Defense in Depth
Why delimiters are not a sandbox, how indirect injection reaches agents, and which architectural controls actually reduce impact.

Apply the category

Put this against a real system.

If a decision in Evaluation and Security is in front of you right now, the fastest version of this is a call: bring the architecture, the failure you are seeing, and the constraint you cannot move.

Discuss the system

In the age of AI

The advantage was never the model. It's knowing what to build with it — and having a team that can actually ship it.

That's the part I help with: finding where AI genuinely makes your business faster, deciding what's worth building, and standing behind it once it's live.

Let's build it together See how we'd start

Four offices, one very full passport