ONLINE
Bento

AI Agent Setup

Bento docs are available as browser pages and clean markdown so coding agents can read implementation guidance directly.


Goal

Give your agent enough Bento context to choose the right integration path, read the relevant SDK README, and avoid common mistakes around credentials, consent, and deliverability.


Agent Prompt

Use this prompt in Cursor, Claude, Codex, or another coding agent:

Read https://bentonow.com/agent_onboarding.md and talk with me about how we should implement Bento. Follow the docs/SDK links based on what platform we use, and prefer the .md version of Bento docs pages when reading documentation directly.

Machine-Readable Docs

Useful entrypoints:

  • /llms.txt: short index for agents and crawlers.
  • /agent_onboarding.md: implementation guidance.
  • /docs-index.md: all docs pages.
  • /docs/quickstart.md: markdown version of a docs page.
  • /api/docs/raw?path=/docs/quickstart: raw markdown API for one page.

Implementation Guardrails

Tell your agent:

  • Ask whether the goal is marketing automation or transactional email.
  • Use SDKs when a first-party SDK exists.
  • Keep Bento secret keys server-side.
  • Do not send real production email from local development or CI.
  • Add rate limits to actions that send email.
  • Set up sender authentication before production sending.

Was this page useful?

Your answer helps us find docs that need work.