AI red teaming · Independent · Evidence before conclusionsOne workflow, two business days
Independent AI red teamingPractice / 02

Someone will attack your AI.Let the first one be me.

Independent AI red teaming for generative AI products, copilots and agents. I attack them the way adversaries will: jailbreaks, prompt injection, data theft, tool misuse, harmful outputs. Under written rules, before real users meet them.

  • Reasoning inspectable
  • Tooling open source
  • One name on the conclusion
Joey Victorino
Joey VictorinoIndependent AI red teamer · Las Vegas

For product teams shipping LLM features, companies handing AI agents real permissions, and the security leaders and counsel who have to put their name under "safe to launch". Campaign counsel and clinics adopting an AI scribe: see Special Situations.

Scroll to explore
01 / Why nowAI that acts can be made to act

Think like the attacker.
Write like a witness.

I find the paths an attacker would take through your AI, prove each one so a stranger can reproduce it, and stay until the fix holds.

The practice I follow is published, the tooling is open source, and my name is on every conclusion.

Examine the work
02 / Research & judgmentFollow the reasoning. Challenge the assumptions.

A good idea has to
survive the evidence.

What is the strongest alternative? What does the entire system cost? Which test would change the decision? I make those questions explicit before recommending what to build or trust.

Inspect the analysis and working model
  • Read the argument.Research, scaling and the path from a result to real use.
  • Change the assumptions.A live cost model with a separate test of what the evidence supports.
  • Inspect the engineering.Public code, a proposed experiment protocol, and explicit limits.
04 / How we workDefined scope. Written terms.

Choose your
beginning.

One conversation. One engagement. Or one person who runs the red team for you.

Fixed projects use a written scope and include a retest window. The retainer uses an agreed monthly capacity. A briefing or training day costs $10,000/day.

05 / Beyond the AI systemSame method. Same person. Other targets.

When the target is not
an AI system.

An adversary's view and a witness's standard of evidence travel well. Two more lines run on them.

For counsel and family offices: SUBROSA // OS, explained in plain English — software for an organized, source-linked review. Try the synthetic demonstration.

Joey VictorinoJoey Victorino / Independent AI red teamer

The person behind the work

You meet me.
I run the red team.

I perform the engagement myself, threat model to retest. No handoff to a junior team. One name on the conclusion.

About the practice
A finding stays theorized until a stranger can reproduce it from my notes.
The standard every engagement is held to. Read what a validated finding contains
06 / The methodPublished practice

Nothing proprietary.
Everything inspectable.

The method is public.
The judgment is mine.

I follow the practice Microsoft's AI Red Team has published and Anthropic's public offensive security posting describes: understand what the system can do and where it is used, model the actors and their tactics, test security failures and harmful outputs together, automate for coverage while a person judges the results, and work break-fix cycles with the product team until the retest closes. I am independent of both companies.

Read the practice I follow
07 / Open for inspectionRead before we speak.

Claims invite questions.
Work invites inspection.

Read the research and decision model, then inspect the code. The artifacts show method; they do not establish a client result.

More public workTasia ↗ORBIT ↗
What I don't do

Clear limits.
From the beginning.

I do not test without written authorization, promise that a system is safe, or run a round-the-clock desk. If the program needs a larger team, I say so early.

Scope, methods, and limits

A place to start

Bring the system.
I’ll bring the adversary.

Start a one-workflow red team · $3,500 flat