> For the complete documentation index, see [llms.txt](https://docs.sire.bot/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.sire.bot/how-it-works/editor.md). # Overview SIRE operates as a multi-layered intelligence network that transforms real-world sports data into on-chain execution. It combines computer vision, quantitative modelling, and AI-agent automation to detect inefficiencies and act on them programmatically. #### The Technology SIRE runs on three interlocking layers that transform live sport into deployable intelligence. While elements of this architecture are already powering αVault’s strategies, several components — particularly the advanced vision and multi-source optimisation systems — are actively in development. #### **1. Unique Data Layer** **Score Vision (Bittensor Subnet 44)** is a primary contributor. It converts live video into tracking-grade coordinates and events, then packages **Vision-Language-Action (VLA)** and **Player Value Function (PVF)** insights as contributor “packets.” These packets sit alongside proprietary datasets, live match feeds, market odds, and analyst notes to form a unified, structured stream. #### **2. Quantitative Core** The core combines and reweights multi-source signals in real time. For each target, it: * Ingests contributor packets, including Score’s VLA and PVF outputs. * Fuses them with the SIRE LLM, using multiple passes to estimate fair value and potential edge. * Logs outcomes, scores contributor sources by live calibration and PnL tracking, and reweights on the fly. * Sizes positions using fractional Kelly with explicit edge thresholds.\ The LLM-first design searches large context windows to uncover independent signals for live, adaptive performance. #### **3. Autonomous Agent** Signals surface in the token-gated **aLink** terminal and execute through automated pools and **aVault**. Every decision is recorded from odds to settlement, which keeps performance verifiable and enables continuous improvement. #### Continuous data loop The engine ingests and recalculates every second, incorporating: * Real-time match events and visual streams * Player and team performance metrics * Historical patterns and contextual priors * Market prices, liquidity gaps, and risk parameters The result is a live stream of institutional-grade intelligence that bettors, partners, and automated vaults can use at scale. --- # Agent Instructions This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com. ## Querying This Documentation If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question. Perform an HTTP GET request on the current page URL with the `ask` query parameter, and the optional `goal` query parameter: ``` GET https://docs.sire.bot/how-it-works/editor.md?ask=&goal= ``` `ask` is the immediate question: it should be specific, self-contained, and written in natural language. `goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal. The response will contain a direct answer to the question and relevant excerpts and sources from the documentation. Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.