Adversarial AI Testing
Find your model's failure modes before someone else does
I help AI teams stress-test production LLMs — probing for prompt injection, jailbreaks, data extraction, and behavioral drift — and deliver a clear report of what's exploitable and how to fix it.
What I offer
Engagements
Each engagement is scoped to your model, deployment context, and risk profile. All findings are delivered as a written report with reproduction steps and mitigations.
Red team assessment
A structured adversarial evaluation of your LLM — prompt injection, jailbreak coverage, data extraction vectors, and behavioral edge cases.
From $5,000 / projectOngoing retainer
Monthly red-teaming for teams shipping frequently. Continuous coverage as your model and prompts evolve.
From $4,000 / moAdvisory & scoping
Hourly advisory for teams that need a technical sounding board — threat modeling, eval design, or pre-launch risk review.
$200 / hrAdversarial AI knowledge base
Published research & guides
Practical writing on LLM failure modes, attack classes, and testing methodology.
Eight ways an airline chatbot fails
A taxonomy of failure modes for customer-facing LLMs in regulated, high-stakes deployment contexts.
System prompt leakageFive ways your system prompt leaks to users
Direct probing, encoded extraction, roleplay attacks, multi-turn escalation, and differential analysis.
SycophancySycophancy is an enterprise liability
When a model tells users what they want to hear instead of what's true, the consequences range from bad advice to legal exposure.
Prompt injectionIndirect prompt injection via RAG-retrieved documents
How attackers embed malicious instructions in documents your model retrieves, and four specific attack patterns to test for.
Hi, I'm Sean
20+ years in software quality engineering, most recently as QA Manager at Providence Digital Innovation Group where I led adversarial testing for Grace — a patient-facing OpenAI-based chatbot handling appointment booking, prescription management, and symptom checking in a HIPAA-regulated environment.
I started Black Diamond Consulting to do focused, independent adversarial testing — without the overhead of a large firm and without compromising on rigor.
Engagement intake
Fill this out and I'll follow up within 2 business days. I'll send an NDA before our first call if needed.
I'll follow up within 2 business days.