# Guides

Plain answers to the questions developers ask when they give AI agents APIs, budgets and tools.

- [How to give an AI agent access to many APIs](https://arettic.com/guides/give-ai-agent-access-to-apis.md): Three ways to connect an agent to many APIs, what each costs you in keys, bills and code, and how to do it with one key.
- [Can an AI agent choose which API to call?](https://arettic.com/guides/let-agent-choose-api-provider.md): Yes. How to let your agent pick a provider for each job at runtime instead of hardcoding one, and how to keep that choice honest.
- [How to set spending limits for AI agents](https://arettic.com/guides/ai-agent-spending-limits.md): Why limits belong in the API and not in the agent's prompt, which limits to set, and what should happen when an agent hits one.
- [How AI agents should handle API failures](https://arettic.com/guides/handle-api-failures-in-agents.md): Errors, empty answers and wrong answers: how an agent can tell them apart, when to retry, when to switch provider, and how not to pay for failures.

This page as HTML: https://arettic.com/guides · Markdown: https://arettic.com/guides.md · JSON: https://arettic.com/guides.json