One operator, real models, verifiable results.
ZenHodl is a sports modeling and edge platform built by Coy Evans. The live platform, API, datasets, and course all point back to the same core idea: model the game state independently, then compare that estimate to the market.
The product is AI-assisted on the software side, but the trust layer is intentionally human-readable: live results, validation, methodology, and on-chain settlement are all visible so you can inspect the work instead of taking marketing claims on faith.
Edge scanner, fair lines, live game states, and monitoring across 7 sports.
REST and WebSocket access for games, edges, predictions, venues, and webhooks.
6 notebooks showing how the modeling, backtesting, and deployment pipeline was built.
Training datasets, snapshots, and validation work used to support the model layer.
A trustable alternative to circular “fair value” tools.
ZenHodl started from a simple frustration: most sports quant tools either derive value from sportsbook odds, which makes the signal circular, or they sell polished backtests without showing live outcomes.
The model stack here is built from game state, historical outcomes, and rating context first. The market is something to compare against, not something to copy.
That same model layer powers the live platform, the API, the course examples, and the validation pages. The point is consistency: fewer disconnected stories, more inspectable output.
Win probabilities are estimated from the game, then compared to the market instead of reverse-engineered from it.
The course, API, and platform are not separate stories. They point back to the same modeling foundation.
Live results, methodology, validation, and chain-level settlement links are all public because trust should survive inspection.
Coy Evans
Founder, operator, and system owner
Coy owns the modeling direction, product decisions, validation standards, and trading workflow. The site is intentionally built to show the work rather than hide behind vague claims.
That means the public pages have to do more than sell. They need to explain what the system is, what it is not, and how someone can verify it before paying for anything.
AI-assisted development
Software built with coding copilots, disclosed on purpose
A meaningful part of the codebase has been built with AI coding assistants. That includes implementation help, refactors, debugging, documentation, and infrastructure work.
We call that out because it is better to be explicit than pretend every line was handwritten in isolation. The trust question is not who typed the loop. It is whether the product, results, and validation hold up in public.
If a claim matters, there should be a place to inspect it.
Live trades settle publicly on Polymarket and can be cross-checked on PolygonScan.
Wins, losses, and filtered bot-attributed results are visible instead of hidden behind screenshots.
Confidence intervals, calibration, p-values, and error analysis are published with the model story.
The public methodology explains what goes into the models and where the limits are.
Try the live platform first
If you want signals, API access, and live monitoring without building the stack yourself, start with the platform.
See pricing →Learn how the system was built
If you want the notebooks, modeling workflow, and deployment path, the course is the build-it-yourself lane.
Open the course →