Approvals & safety

Guardrails for AI-drafted posts

Guardrails check every draft before it reaches your inbox, and again before it publishes. Some reject a draft outright; others flag it for you.

How to do it

  1. List banned topics In brand memory, add topics agents must never post about. Drafts that match are rejected.
  2. Rely on per-network length Each target network is checked with its own rule. Nothing to configure.
  3. Set daily limits Set a maximum number of posts per account per day for agent-driven posts.
  4. Review warnings Link shorteners and missing alt text are flagged on the draft so you can fix them before approving.
  5. Keep rules in your repo Put banned topics in .socialhandoff/policy.json and apply them with pnpm socialhandoff policy apply, so changes go through review.

What each guardrail does

GuardrailResultNotes
Banned topicsRejected (422)Matched against the draft text
Per-network lengthRejected (422)X weighted 280, Bluesky 300 graphemes, Mastodon 500, LinkedIn 3,000
Daily limit per accountRejected for agentsOwners approving by hand may go over it
Missing alt textFlaggedShown on the draft
Link shortenersWarningThe draft still lands in the inbox

Daily limits and humans

Daily limits are enforced whenever no person is in the loop: a direct agent schedule, or an agent approval under auto-publish, that would pass the limit fails. You can still approve an extra post by hand.

Guardrails and the trust ladder

A guardrail failure demotes the agent that wrote the draft to draft-only immediately. That keeps an auto-publishing agent from repeating a mistake.

Why length is a guardrail

A scheduler that counts length the wrong way accepts a post and then fails at publish time, often overnight. Checking with each network's own rule at draft time moves the failure to where you can see it. Try the cross-post length checker to see the same rules.

See the guardrails glossary entry and prompt injection for why agent output needs checks.

Frequently asked questions

Can an agent get around a guardrail?
No. Guardrails run on the server for every draft, whatever the key's permissions.
Why was my own edit rejected?
Guardrails run again on your edits. An edit that makes a post too long, or adds a banned topic, is rejected the same way.
Are link shorteners blocked?
They are flagged as a warning. The draft still reaches the inbox, and you decide.

Let your agents post. Keep the final say.

Connect your first agent in minutes. Every draft waits in your inbox until you approve it.

14 days free. No card required.

The hosted version is opening soon

Leave your email and we will send one message when hosted accounts open, with your 14-day trial ready. Want it today? Self-host it free from the repo.

Start free trial