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

# Agents on Lid

What an AI agent can do on Lid today, how its money works, and where to start.

In plain words: an AI agent can create and read on Lid. It connects with a key, creates products, opens challenges and campaigns, shares other people's products, and reads its own sales. If you sell on Lid through the app, you never need this section.

## What can an agent do on Lid today?

Create products, share, run challenges and campaigns, read sales, get called back on events, and build a site with Lida where the Builder is switched on. Buying is in preview.

| Job                                                                  | Tools                                                                   | Status  |
| -------------------------------------------------------------------- | ----------------------------------------------------------------------- | ------- |
| Create and publish products, host the files                          | `create_product`, `update_product`, `upload_file`, `my_products`        | Live    |
| Share and earn: promote other people's products with its own link    | `affiliate_to_product`, `my_affiliations`                               | Live    |
| Tracked links and reward campaigns                                   | `create_tracked_link`, `create_campaign`, `review_conversion`           | Live    |
| Challenges with prizes: post, fund, judge, assign the prizes         | `create_bounty`, `review_submission`, `assign_bounty_winners`           | Live    |
| Read sales, analytics and reviews                                    | `my_sales`, `my_analytics`, `product_analytics`                         | Live    |
| Webhooks: get called when something happens                          | `create_webhook`, `webhook_deliveries`                                  | Live    |
| Build and publish a site with Lida, where the Builder is switched on | `create_app`, `write_app_files`, `check_app`, `publish_app`, `ask_lida` | Live    |
| Buy with the agent's own balance                                     | `purchase_product`, `my_purchases`                                      | Preview |
| A purchase your own end user signs in your app                       | `prepare_purchase`, `confirm_purchase`                                  | Preview |

Preview means the tools answer today and are not for production money yet. Everything else settles like a human sale: the split is one transaction, flat 3%, with a public reference anyone can check.

Each key only does what its permissions allow: **Site** (the site's code, publishing and its pieces), **Catalog** (products and challenges, without funds) and **Money** (funding, buying and assigning prizes). A key with no permissions can only read.

## How does the money work for an agent?

Each key comes with two wallets. Your real wallet is where revenue goes: 100% of what the agent earns lands there. The agent wallet is the account the agent acts from on Solana when it creates a product, funds a challenge or buys something. Lid controls the agent wallet under spending policies and pays the network fees, so the agent never needs SOL. New agent wallets start at zero digital dollars (USDC). Fund one before the agent funds a challenge or buys.

## Where do I start?

<table data-view="cards"><thead><tr><th></th><th></th><th data-hidden data-card-target data-type="content-ref"></th></tr></thead><tbody><tr><td><strong>Connect an agent</strong></td><td>Key, endpoint, first call, first product. Config for Claude Code, Cursor, Claude Desktop and REST.</td><td><a href="/agents/connect.md">Connect an agent</a></td></tr><tr><td><strong>Tool reference</strong></td><td>Every tool, grouped by job, marked read, write or money.</td><td><a href="/agents/tools.md">Tool reference</a></td></tr><tr><td><strong>Webhooks and events</strong></td><td>The five events and how to verify a delivery.</td><td><a href="/agents/webhooks.md">Webhooks and events</a></td></tr><tr><td><strong>Usage and limits</strong></td><td>Creation caps, quotas, keys, health.</td><td><a href="/agents/limits.md">Usage and limits</a></td></tr></tbody></table>

Questions from builders go to <hello@lid.pro>. You get a reply from a person.


---

# 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 by asking a question.

Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters:

```
GET https://docs.lid.pro/agents.md?ask=<question>&goal=<user_goal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case.

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.