---
title: Best practices
description: Short patterns for calling Formats and Agent Completions well — with copy-paste examples.
---

A few patterns that keep partner integrations boring and reliable. Use the
interactive examples below as a starting point; swap the handle, slug, and
instruction for your account.

## Prefer a Format over raw model calls

When you have a saved recipe, call it by handle and slug. The Format owns the
tooling, spend gates, and house style — your client only sends the brief.

<!-- api-call-example:format-vanity-run -->

See [Calling a Format](/formats/call) for the full contract, and
[Structured output](/formats/structured-output) when you need typed JSON back.

## Bind a schema when a system will consume the result

If another service will read the receipt, bind `output_schema` so you get a
validated object instead of free text. Require only fields the Format actually
produces.

Full rules: [Structured output](/formats/structured-output).

## Use Agent Completions for one-off work

When there is no saved Format yet — or the brief changes every time — send an
Agent Completion with a spend cap.

<!-- api-call-example:agent-completion -->

## Keep credentials scoped

Use a **team** API key for Formats provisioned on a team handle. Prefer the
narrowest scopes your client needs, and rotate keys from the
[Dashboard](/dashboard/api-keys).

## Cap spend on every run

Always set `generation_spend_cap_usd` (and an agent cap when relevant). Treat
missing caps as a bug in the client, not a convenience.