Guides
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
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?
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
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
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.