> 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/predictions.md).

# Predictions

> **Status: not live yet.** Prediction markets are on Archer's near-term roadmap. This page outlines what we're building so the surface is documented as it ships.

## What Predictions Will Look Like in Archer

Prediction markets let you take a position on a real-world outcome — election results, sports outcomes, macro events, regulatory decisions — and earn if you're right. Today this means signing up at Polymarket or Kalshi separately, funding each platform individually, and managing claims after resolution by hand.

In Archer, you'll just say what you think:

* *"Bet $50 that the Fed cuts rates in June"*
* *"Take YES on the Solana ETF approval at any price under $0.65"*
* *"What are my open prediction positions?"*
* *"Claim my winnings on the election market"*
* *"Show me the most-traded political markets right now"*

Archer routes to the venue with the best odds and deepest liquidity, funds from your existing balance, places the position, and tracks resolution automatically. When a market settles, claims are surfaced in your dashboard or auto-claimed if you've enabled it.

## What We're Building Toward

* **Multi-venue.** Polymarket (Polygon-native), Kalshi (US-regulated), and emerging on-chain prediction protocols. Best price across all of them.
* **Market discovery.** *"What markets are open about the Fed?"* should return ranked, currently-trading markets with USD volumes and current odds.
* **Outcome tracking.** Open positions show in your portfolio with current mark-to-market value, resolution date, and the live odds.
* **Auto-claim.** Optional toggle — when a market resolves, winnings claim automatically to your wallet.
* **MCP tool surface.** `place_prediction`, `get_open_predictions`, `claim_prediction_winnings`, `search_prediction_markets` — agents will be able to use prediction markets as a first-class action.

## Why It's Not Live Yet

Predictions add a few complications the current architecture doesn't yet handle:

1. **Long-lived positions with external resolution.** Unlike swaps, predictions sit open for weeks or months and settle based on real-world events. Tracking and claim flows are a separate primitive from one-shot transactions.
2. **Geographic compliance.** Kalshi is US-regulated; Polymarket has restricted jurisdictions. Archer needs to surface eligibility transparently.
3. **Market data quality.** Prediction markets have wide spreads and shallow books on long-tail topics — quote freshness and slippage previews matter even more than for swaps.

We're working through these. Updates will land here as the surface ships.

If you're an active prediction-market user with opinions on venue priority or UX, reach out at [archerprotocol.com/contact](https://archerprotocol.com/contact).


---

# 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/predictions.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.