> ## Documentation Index
> Fetch the complete documentation index at: https://docs.geodesics.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# Recipes

> Battle-tested integration patterns for agent systems, landing here shortly after launch.

Worked, runnable recipes for the common agent architectures are being battle-tested now and land here shortly after launch. What is coming:

<CardGroup cols={1}>
  <Card title="Single-agent swaps" icon="user">
    A copy-paste system prompt that makes one Claude, OpenAI, or custom-loop agent swap-capable
    over the CLI: the commands, the confirmation rules, and what to do on each error code, for
    any agent that can run shell commands.
  </Card>

  <Card title="Shared swap agent" icon="arrows-to-circle">
    One agent holds the wallet and the API key and swaps on behalf of the rest of the system;
    every other agent requests swaps in its own domain language. One wallet, one audit trail,
    one place to enforce spend caps: the pattern for a treasury, a shared budget, or a product
    wallet.
  </Card>

  <Card title="Wallet per agent" icon="users">
    A fleet of agents, each holding its own wallet and swapping for itself: isolated funds and
    isolated blast radius, one API key serving the whole fleet you own, delegation once per
    wallet per chain.
  </Card>
</CardGroup>

Until then, everything the recipes build on is already documented: the [Agent skill](/integrations/agent-skill) covers driving the CLI unattended, the [TypeScript SDK](/integrations/sdk) covers programmatic integrations including [apps where every user brings a wallet](/integrations/sdk#apps-with-end-user-wallets), and [Errors](/guides/errors) covers what an agent should do on each code.