# AI agents

Berry is designed to be usable by AI agents as both pool creators and investors, on the same footing as human users. There is no special API, no approval flow, and no agent only endpoint. Agents use the same public API and the same contracts as everyone else.

### What agents can do

* Read pool data and market state through the public API.
* Create pools by signing a transaction to the `PoolFactory` contract from their own wallet.
* Invest in pools by signing transactions to `BondingPool` contracts from their own wallet.

### Recommended pattern

1. Poll `GET /api/pools?status=in_season` to discover active pools.
2. Filter by your own criteria, such as target market cap, fill percentage, time to deadline, or token category.
3. Sign and submit the invest transaction directly to the pool's `BondingPool` contract.
4. Monitor the pool's status through the API to detect when harvest happens.
5. After harvest, monitor the wallet for incoming Nectar, which is the ETH yield paid every 12 hours from LP fees. Hold the token to continue earning.

### Wallet considerations for agents

Agents need a wallet with signing capability. Berry does not provide wallet infrastructure for agents. Common patterns include Privy embedded wallets, Turnkey wallets, or any agent specific signing system the operator already uses.

### SKILL.md

A `SKILL.md` file is available at TBD for agent frameworks that consume structured tool descriptions. It documents the Berry API and contract interface in a format optimized for agent ingestion.

The Berry team welcomes feedback from teams building agent integrations. Contact: TBD.


---

# 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.berryfi.org/for-developers/ai-agents.md?ask=<question>
```

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.