> For the complete documentation index, see [llms.txt](https://eosi-finance-1.gitbook.io/eosi-finance-documentations/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://eosi-finance-1.gitbook.io/eosi-finance-documentations/eosi-finance/8-ai-agent-and-strategy-marketplace/8.2-types-of-agents-and-capabilities.md).

# 🧩 8.2 Types of Agents and Capabilities

#### 🧩 8.2 Types of Agents and Capabilities

<mark style="color:$primary;">**EOSI Finance**</mark>’s agent marketplace can feature:

1. **Discovery Agents:** bots that help users explore yield opportunities and trending narratives. Examples include yield discovery (real‑time APYs across protocols), sentiment analysis (social media trends) and fundamental analysis (project metrics).
2. **Execution Agents:** bots that implement multi‑step strategies across protocols. Capabilities include bridging assets between chains, swapping tokens via DEX aggregators, lending and borrowing from money markets, trading yield tokens, staking and providing liquidity. Users can execute complex strategies with one click.
3. **Portfolio Agents:** bots that manage long‑term portfolios, rebalancing across asset classes. They may track a 60/40 crypto/RWA portfolio, allocate to stablecoin yield farms or adjust risk according to market volatility.
4. **Social Agents:** bots that translate social trading insights into executable strategies. For instance, when a renowned trader posts a DeFi strategy on Twitter, a social agent could convert it into a trade template accessible to <mark style="color:$primary;">EOSI Finance</mark> users.
5. **Custom Agents:** users can build custom agents via natural‑language prompts. The platform converts prompts like “Swap 1 ETH to USDC, deposit into Aave, borrow 50% collateral, buy RWA tokens” into executable smart contract calls


---

# 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://eosi-finance-1.gitbook.io/eosi-finance-documentations/eosi-finance/8-ai-agent-and-strategy-marketplace/8.2-types-of-agents-and-capabilities.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.