# Agents tl; dr
{% hint style="success" %}
*"A useful definition of solvers is self-interested actors who are financially incentivized and rewarded for their participation and optimization."*
\- Nathan Worsley
{% endhint %}
A [**MEV agent**](https://docs.urani.trade/mev-agents/agents) is a term we coined to denominate an **algorithm (or bot)** authorized by the[ **Urani Protocol**](https://docs.urani.trade/urani-protocol/urani-protocol-overview) to receive [**intent**](https://docs.urani.trade/urani-swap/technical-considerations/uranis-intents) [**batches**](https://docs.urani.trade/urani-swap/technical-considerations/batch-auctions) and return[ **optimized solutions**](https://docs.urani.trade/urani-protocol/technical-considerations/optimization) for orders.
A **MEV agent operator is the human** who operates this bot. Typically, they are developers who want to take advantage of multiple trading strategies in cryptomarkets.
Agents are essential components of the protocol, functioning as matching engines to identify the optimal execution paths for orders to ensure traders receive the best execution, *i.e.*, the most advantageous prices and routes.
{% hint style="info" %}
We like to think that our MEV agent templates are "customizable skateboards", allowing operators to navigate the hypergraph of the orderflow auction landscape.
{% endhint %}
***
## How MEV Agents Work
At a high level, agents first analyze the current batch of orders to detect any P2P matches or ring trades that could offer the best prices for [**executing trades or limit orders**](https://docs.urani.trade/urani-swap/technical-considerations/order-types).
If no such match is found, they deploy their [**graph and combinatorial algorithms**](https://docs.urani.trade/mev-agents/operator-onboarding/setting-up-an-agents-graph) to solve the problem by evaluating multiple factors, including liquidity, orderbook depth, price slippage, and exploring multiple venues, including on-chain automated market makers, DEXs, and aggregators.
---
# Agent Instructions: 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:
```
GET https://docs.urani.trade/mev-agents/agents.md?ask=
```
The question should be specific, self-contained, and written in natural language.
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.
