Watch my NBC News interview
I walk through the project with Tom Llamas, including the visible signals it measures and its use in poker coverage.
Watch the interview on LinkedInThe video is hosted on LinkedIn, which may ask you to sign in.
Project showcase
AI Poker Tells Detection
I built an experimental computer-vision system to study visible player behavior in recorded poker footage. Omaha Productions featured the project during ESPN's 2026 WSOP Main Event coverage. This page explains the research, its media coverage, and its limits.
ESPN 2026 WSOP Main Event broadcast
NBC News interview
WIRED
Sportico
AI poker tells detection
Poker bluff detection AI
Poker tells
Computer vision poker
Poker AI
WSOP Main Event
ESPN poker broadcast
Watch the interview and explore the work
In my NBC News interview, I explain how the poker tells project uses video to study player behavior.
Watch the video in my public LinkedIn post, read the project background, or explore PokerStreamClipper, my separate tool for finding hands and preparing highlights.
Understand the analysis
Learn how camera footage, player-specific baselines, and repeated behavior inform the analysis, and why a physical signal is not proof of a bluff.
Read the poker tells explainerThis is a high-level explanation, not public access to the private model or code.
Find hands with PokerStreamClipper
Choose a supported recording, find a player or large pot, preview the detected hand, and prepare clips for your editing workflow.
Explore PokerStreamClipperThe clipper is a separate product, not a live bluff detector.
What It Does
The AI poker tells detection system studies video of a player across many hands and looks for repeated physical patterns associated with that player's hand strength. Those patterns depend on the available footage and the individual player, and some players show no useful signal. A flagged moment is a probabilistic observation for review, not proof of a bluff or a live-play recommendation.
On ESPN's Main Event coverage the feature was used responsibly: analysis was shown only for players after they had been eliminated, so nothing on the broadcast could influence live play.
Blink rate
Changes in blink frequency under pressure, compared against the player's own baseline.
Eye gaze
Where a player looks (the board, the chips, the opponent) and how that shifts by hand strength.
Posture & stillness
Shifts in posture and sudden changes in stillness after betting.
Smile symmetry
Asymmetric smiles read differently than genuine ones, one of many micro-expression cues.
How the model combines these signals (the architecture, the training data, and the code) is private. This page is a showcase of what the system produces, not a technical write-up. For the high-level ideas, read Can Poker Tells Be Measured With Computer Vision?
Honest limits: the system needs footage of a player to find their patterns, and some players simply don't have detectable ones. As Luke put it: "If I deployed it on a top professional like Daniel Negreanu, the system would probably find no signals. I assume he's worked hard to eliminate them."
As Featured On
- ESPN: 2026 WSOP Main Event Omaha Productions featured the AI tells detection system on ESPN's World Series of Poker Main Event coverage, using it to break down the behavior of eliminated players.
- NBC News Watch Luke Geel's NBC News interview with Tom Llamas in Luke's public LinkedIn post.
- WIRED WIRED's feature on the AI tells detection system at ESPN's World Series of Poker, how an AI tool that reads body language made it onto the Main Event broadcast, and where the technology could go next.
- Sportico World Series of Poker Enlists New AI Tool That Tells When You Bluff
- ZME Science ESPN Is Bringing Back the World Series of Poker, This Time with AI That Spots Players Bluffing
- BroBible ESPN Debuts New AI Technology For World Series Of Poker To Show If Players Are Bluffing
- SoMuchPoker AI Can Detect Poker Bluffs? The Future of Poker Is Here
- PokerStrategy Can AI facial recognition really identify facial tells or are we being bluffed?
- Spade Poker Revolution at WSOP 2026: ESPN Deploys AI to Spot Bluffs
- Luke's project update Read Luke's first-person update about the NBC appearance.
Common Questions
Who built the AI poker tells detection system?
I'm Luke Geel, a Boston-based AI engineer, poker player, and poker technology writer.
I built the experimental poker tells system and the separate PokerStreamClipper product.
What is AI poker tells detection?
A computer vision system that analyzes poker players on video (blink frequency, gaze, posture, stillness, and micro-expressions) and compares those patterns against previous hands to flag likely bluffs and likely strong hands.
Was it really on ESPN?
Yes. Omaha Productions featured the system on ESPN's 2026 WSOP Main Event coverage, applied only to players who had already been eliminated.
Can AI really detect poker bluffs?
Sometimes. It finds player-specific patterns when there is enough footage, and it is honest when there is no signal; some players, especially elite pros, don't have detectable tells.
Can I see the code or use the tool?
The code and methodology are private. For media, licensing, or collaboration inquiries, contact geelluke@gmail.com.