Raul Moriarty

Background

I am Communications Lead at Poker Bot AI, the parent project behind this site, and have spent the last decade and a half working at the intersection of software product development, business development, and online poker technology. My role has put me in regular contact with engineers building decision engines, operators thinking about platform integrity, and customers who care about whether the underlying claims about modern poker software are actually true. That last group is why this site exists.

Most public writing on "GGPoker bots", "hacks", and "cheating" comes from one of two angles: a marketing surface pretending that solver-anchored AI is a server exploit, or a forum thread treating any kind of automated decision support as the same thing as deck-prediction snake oil. Both of those framings are wrong, and they keep otherwise informed readers from understanding what real poker software does, where the engineering problems are, and what an operator like GGPoker is actually doing on the detection side.

Areas of focus

The threads I keep returning to in poker software:

Modern poker software architecture

Solver-anchored baselines (CFR-family outputs from PioSolver, GTO+, MonkerSolver) compressed into runtime-queryable policies, paired with online opponent models that converge inside a session rather than across years of HUD data. The interesting engineering work is in the inference budget and the policy combiner, not in the headline math.

The GGPoker ecosystem

Anonymous tables, rotating screen names, operator-controlled HUDs, and PokerCraft analytics — the architectural choices that shaped the modern problem. NSUS Group's platform is the most-studied operator in the network, and most of the practical questions readers send in are GGPoker-flavoured.

Detection from the operator side

The four-layer model (behavioural fingerprinting, statistical play-pattern analysis, anti-collusion graph models, human review) and where naive software gets caught. This is the part of the field that benefits most from being explained honestly — not as a checklist of "how to avoid bans" but as an adversarial-classification problem with an asymmetric cost matrix.

Business and product

Fifteen years in software business development gives me a useful filter on which claims about poker AI are real engineering and which are pure sales copy. A lot of what passes for "poker hack" marketing is the latter, and saying so plainly seems to be more useful to readers than another carefully neutral overview.

Game theory in practice

Where the math says "stop." Some spots in poker are solved well enough that further automation is rounding error; others — deep-stacked multiway turn play, ICM-heavy MTT endgames — are still meaningfully open. Knowing the difference is part of taking the field seriously.

About this site

Three long-form notes (hacks, detection, FAQ) plus the homepage cover what I think is worth saying publicly about the GGPoker ecosystem right now. Pages are revised when the field changes; dates at the top of each piece are the last revision, not the original publication.

If you have a question about anything covered here — implementation, the detection picture from the operator side, or the business reality behind a particular "hack" product — the chat link below goes to the Poker Bot AI team and I read what comes in. Developers, researchers, and curious players are all welcome.