Marketing and editorial

Check content against your brand and editorial guidelines before it’s published.

Style guides are long and nobody rereads them before hitting publish. Turn the rules that matter, like promises you can’t make, claims that need a source, and comparisons legal must see, into a check that runs on every draft.

Start freeSee an example

More content, same number of editors

Teams now produce more drafts than ever, many with AI help, and reviewers can’t read them all closely. The mistakes that cause trouble are predictable: a claim without a source, a sentence that quietly promises results, a casual jab at “the big players” that legal never saw.

A check before publishing catches those consistently and leaves the editor’s attention for voice and quality.

Where the check fits

One call between the step that prepares something and the step that sends, publishes, or runs it. Your code applies the decision.

See it decide

The same policy evaluated on three cases. Pick one and run the check to see which evidence it relies on.

Policy

Copy must never promise or guarantee results, whether stated outright or implied. Universal or superlative claims about Acme Cloud need a source in data.sources that supports them. Any comparison with competitors, named or clearly implied, goes to legal review.

data

{
  "draft": "Acme Cloud cut deploy times by 38% for teams in our 2026 customer survey.",
  "sources": [
    "2026 customer survey, n=412: median deploy time down 38%"
  ],
  "type": "feature page"
}

Result

violationProbability—
reviewProbability—

Why: The claim is specific, attributed to the survey, and the source supports the number.

Your code: Publish.

Response JSON
{
  "decision": "allow",
  "allowed": true,
  "violationProbability": 0.05,
  "reviewProbability": 0.07,
  "policyId": null,
  "policyVersion": null,
  "requestId": "req_7f3a…"
}

Illustrative example. Real probabilities depend on your policy wording and the evidence you send.

allow · Sourced claim

The claim is specific, attributed to the survey, and the source supports the number.

deny · Implied guarantee

It never says “guaranteed”, but “stop worrying about downtime” and “your revenue is safe” promise an outcome, with no source behind it.

review · Implied competitor

No competitor is named, but “the big hyperscalers” clearly points at specific companies, so the comparison goes to legal.

Where to run it

Anywhere content moves to “published”: a CMS webhook (Sanity, Contentful, WordPress), your social scheduler’s API, or a pull request check for a docs or marketing site. Send the draft, its type, and the sources the author cited.

Set it up

  1. 1

    Extract the enforceable rules

    Pick the guideline lines a reviewer would actually block on: claims, implied promises, comparisons.

  2. 2

    Check on publish

    Trigger the check when a draft changes to “ready” or before the publish API call.

  3. 3

    Route to the right person

    Use review for legal and deny to send it back to the author with the reason.

CMS pre-publish webhook
import { Enforly } from '@enforly/sdk'

const guard = new Enforly({ apiKey: process.env.ENFORLY_API_KEY })

export async function onBeforePublish(doc) {
  const result = await guard.check({
    policyIds: [BRAND_POLICY_ID, CLAIMS_POLICY_ID],
    data: { draft: doc.body, type: doc.type, sources: doc.sources },
  })
  if (result.allowed) return { publish: true }
  return { publish: false, assignTo: result.decision === 'review' ? 'legal' : doc.author, results: result.results }
}

Full request and response fields are in the API reference. Using a coding agent? Point it to Build with AI.

What Enforly doesn’t do

Enforly evaluates the information you send and returns a decision. It doesn’t run operations, and it doesn’t guarantee safety or compliance on its own.

  • Enforly checks rules you can state. It doesn’t judge whether copy is good or on brand in tone unless you describe what that means.
  • It doesn’t provide legal advice. Use it to route content to the people who do.
  • Long documents must fit in the 32,768-character request limit; check sections separately if needed.

Questions

Can it check tone of voice?

If you describe it concretely (“never blame the customer for a problem”, “don’t talk down to beginners”), yes. Vague rules like “sound premium” produce vague decisions.

Does it fix the copy?

No. It returns a decision; the author or your AI writer revises and you check again.

Related

Outbound messagesCheck AI-written emails and customer replies before they’re sentRead MarketplacesAutomated marketplace listing moderation with your own rulesRead Content moderation APIContent moderation API with custom rulesRead

Try this policy on your own data.

Copy the policy above, add your real examples, and see the decision. 200 free checks per month, no credit card.

Start freeBrowse policy templates