> For the complete documentation index, see [llms.txt](https://agent-ted.gitbook.io/agent-ted/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://agent-ted.gitbook.io/agent-ted/features/teds-betting-infrastructure.md).

# TED's Betting Infrastructure

### AI Trading Infrastructure

#### Core Engine

Agent TED operates an autonomous, algorithm-driven pricing and trading engine.

The system ingests structured real-time sports data and applies deep neural networks to:

* Identify positive expected value (EV) opportunities
* Allocate capital across strategies and risk profiles
* Manage exposure dynamically based on model confidence

#### Learning & Adaptation

TED’s models continuously update through statistical feedback loops.

Using cross-entropy loss and outcome validation, the system:

* Adjusts weightings across leagues, teams, and market types
* Incorporates success and failure ratios into future predictions
* Improves long-term performance through convergence, not heuristics

#### Capital & Profit Management

* Position sizing is governed by volatility and bankroll constraints
* Profits are realized and aggregated at the system level
* A portion of realized gains is routed to the Payout Vault for $TED staker distribution