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

# Marketplace Intents

> **Status: groundwork in flight, not yet live.** The infrastructure to publish, rank, and execute developer-built intents is being laid in Phases 1 and 2. The full marketplace surface is the focus of Phase 3.

The intent marketplace is what turns Archer from an execution engine into an *ecosystem*. Today, Archer ships a handful of system-owned intents (Swap, Bridge, Send, Token Lookups, Web Search, Multi-Step). Once the marketplace is live, any developer will be able to publish and monetize their own strategy as an agent that any other user or agent can call (and pay for) by handle.

## How It Will Work

### For Users and Agents

You'll discover and call published intents the same way you call a system intent today — through natural language, via the web app or MCP server. The agent layer is identical.

```
"Run @SolanaSniper on $200 of new launches today"
"Use @YieldRebalancer to rotate my stables to the highest APY"
"Have @ArbBot watch ETH/USDC on Arbitrum for the next 6 hours"
```

Each `@handle` is a developer-published intent with its own logic, fee, and ranking score.

### For Developers ("Vibe Builders")

You'll be able to:

* **Build** a custom strategy or skill using Archer's SDK and tool registry
* **Publish** it as a ranked capability on the marketplace
* **Earn fees** when users or agents execute your intent
* **Stake tokens** on your published strategy as a quality signal and user-insurance mechanism
* **Improve your ranking** by optimizing for reliability, latency, and economic efficiency — higher-ranked intents attract more traffic

### The Ranking Algorithm

Intents are ranked in real time across five factors:

| Factor              | Source                                      |
| ------------------- | ------------------------------------------- |
| Success rate        | Past executions (with confidence intervals) |
| Volume routed (TVR) | Logarithmic scaling of USD value            |
| User sentiment      | Average feedback after execution            |
| Verification        | UNVERIFIED → VERIFIED → PREMIUM             |
| Stake               | Logarithmic scaling of staked tokens        |

Higher-ranked intents surface first when a user prompt matches multiple candidates. Stakes act as economic security; slashing for proven and unmitigated failures keeps incentives aligned and the platform functioning optimally for all participants.

## What's Live Today

The pieces of the marketplace that already exist in Phase 1:

* The semantic-search routing layer that picks intents from a candidate pool
* Per-intent execution telemetry (success rate, latency, value routed)
* Fee collection on swaps and bridges (the platform fee + developer fee mechanic is wired up; we just don't have third-party developers publishing intents yet)
* The intent definition schema (every system intent is published using the same schema developers will use)

## What's Coming

* A developer SDK for building and publishing intents
* An intent composer for low-code workflow construction
* A marketplace UI for browsing and discovering published intents
* The staking and slashing mechanism
* Verification tiers (UNVERIFIED, VERIFIED, PREMIUM)

## Why This Matters

The bet is simple: as agents proliferate, the bottleneck stops being "how do I execute this on-chain?" and becomes "which strategy do I trust?" An algorithmically ranked, performance-scored, economically secured marketplace is the only way that scales. Manual review and walled-garden curation don't.

If you're a developer interested in early access to the marketplace, get in touch at [archerprotocol.com/contact](https://archerprotocol.com/contact).

## Building a Partner Intent

The dispatch path that powers the marketplace is already live on the `test` environment. If you have an MCP server or HTTPS API and want Alice to invoke it by `@handle`, see [Publishing a Partner Intent](/archer.bot/for-builders/publishing-a-partner-intent.md) for a step-by-step guide built around the live `@TokenAnalyzer` reference.


---

# 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://archer-bot.gitbook.io/archer.bot/intents/marketplace-intents.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.