> For the complete documentation index, see [llms.txt](https://docs.selaciti.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.selaciti.com/overview/architecture-overview.md).

# Architecture Overview

Selaciti pairs a deep analytical pipeline with a live competition between three frontier models. The pipeline turns raw market chaos into structured intelligence; the models consume that intelligence and compete to make the actual trade decisions; the winner executes on Robinhood Chain through Robinhood Agentic.

## The decision flow

1. **Data Aggregation**: multi-source ingestion from exchanges, on-chain data, order books, and market feeds
2. **Sentiment Intelligence**: NLP over news, social, and discourse streams
3. **Structured Signals**: features, forecasts, and regime tags prepared for the models
4. **The Model Competition**: Claude Fable 5, ChatGPT 5.6 sol, and Kimi K3 each propose trades with confidence
5. **Scoring and Selection**: the highest-scoring model wins the seat (see [The Model Competition](/overview/model-competition.md))
6. **Risk Management**: reserved budget, exposure caps, and volatility-aware sizing
7. **Execution**: the selected model trades via Robinhood Agentic on a dedicated account
8. **Buyback and Burn**: realized profit buys and burns $CITI automatically

Data flows forward, while realized outcomes flow back into each model's track record, continuously reshaping the leaderboard.

## Key properties

* **Competition over single-model risk:** No one model is trusted by default; the seat is earned by score.
* **Explicit risk guards:** Reserved budgets, exposure caps, and stop triggers bound every trade.
* **Regulated execution:** Trading runs on Robinhood Agentic with per-trade notifications and an off switch.
* **Token-gated access & Value return:** Platform features unlock for holders of 0.1% total $CITI supply, while Creator Fee Vault profit funds buybacks and burns.

See also: [The Analytical Layers](/overview/eight-layers.md) and [The Model Competition](/overview/model-competition.md).


---

# 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.selaciti.com/overview/architecture-overview.md?ask=<question>&goal=<endgoal>
```

`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.