> For the complete documentation index, see [llms.txt](https://sovra-ai.gitbook.io/sovra-ai/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://sovra-ai.gitbook.io/sovra-ai/sovra-ai-documentation/data-flow.md).

# Data Flow

The core functionality of Sovra AI is driven by an intelligent data pipeline that continuously ingests, analyzes, and responds to real-time signals across user behavior, market events, and Virtuals Protocol activity. This pipeline can be summarized in five stages:

1. Event (Input Triggers)\
   Data enters the Sovra ecosystem through various events, both on-chain and off-chain, including:

* Market fluctuations (e.g., price spikes, volume surges).
* Launch of a new Virtuals agent or token listing.
* User actions (e.g., querying Sovra AI, approving a trade, connecting a wallet).
* Sentiment or trend detection from off-chain sources like Twitter, Telegram, and crypto forums.

Each of these events initiates a real-time processing cycle.

2. Analysis (AI Evaluation)\
   Once triggered, Sovra’s AI engine analyzes the event using a blend of on-chain data, historical patterns, and predictive modeling. This involves:

* NLP to understand user intent or message context.
* Reinforcement learning to evaluate similar past actions and optimize future responses.
* Token/project scoring using fundamentals, market behavior, social engagement, and technical indicators.

The outcome is a contextual, personalized analysis tailored to the user’s portfolio and trading goals.

3. Recommendation (AI-Generated Suggestion)\
   Based on the analysis, Sovra generates a strategic recommendation. Examples include:

* “Consider entering XYZ; momentum and community activity are spiking.”
* “Exit ABC: Profit threshold met + early signs of trend reversal.”
* “Stake your idle $VRT for projected 14% APY over the next 30 days.”

Each recommendation includes justifications in natural language, visual insights (e.g., charts or ratings), and suggested actions.

4. Notification (User Alert)\
   The recommendation is delivered to the user through mobile push notifications and/or in-app conversational prompts. Notifications are designed to be:

* Clear, context-aware, and easy to act on.
* Timely, ensuring users can capitalize on opportunities or respond to risks quickly.
* Customizable based on user preferences (e.g., risk appetite, asset focus, trade frequency).

5. Execution (Manual or Autonomous Action)\
   The final step is executing the recommended action. Users have two options:

* Manual Mode: The user reviews and confirms the trade in-app.
* Autonomous Mode: Sovra executes the trade automatically based on pre-approved rules or strategy settings.

All executions are signed securely on the user’s device and broadcasted on-chain via the Base L2 or Ethereum.

🡲 Summary Flow:\
Event → AI Analysis → Strategy Recommendation → User Notification → Execution (Manual or Automated)

This seamless flow allows Sovra AI to function like a personal on-chain trading assistant—always active, always learning, and always adapting to user preferences and real-time market changes.


---

# 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://sovra-ai.gitbook.io/sovra-ai/sovra-ai-documentation/data-flow.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.