CreativeOS writes the ad with the rulebooks already open
Ad generation for regulated categories, where a headline has to clear platform policy, company brand and legal rules, and financial compliance. The rules are structured data the generator reads while it writes, and the same records score the audit afterwards.
In payments, every headline clears three separate rulebooks
Research tells you what the market is doing. AdRadar reads competitor campaigns and TechSpy reads their infrastructure. Neither writes your ads, and at PingPong, a B2B cross-border payments platform, writing them was the slowest part of the whole operation.
A single line of ad copy has to satisfy the platform's advertising policy, the company's own brand and legal rules, and financial compliance on top. Three reviewers, three queues, and a rewrite that sends the draft back to the start of all three.
Speed was never the missing piece. A draft could be produced in twenty minutes and still spend the rest of the week moving between three reviewers who each had a different rulebook open.
One product, one audience, one proof point, rewritten from scratch into four platform formats with four sets of character limits.
per platform, by handGoogle, Meta, LinkedIn and Bing each maintain their own rulebook and revise it on their own schedule.
queue 1The firm's own voice rules, competitor-mention rules, disclaimer requirements and discount limits.
queue 2The third reviewer. A change requested by any one of the three sends the draft back to the front of all three.
back to step 01AI writers, platform review, a banned-words spreadsheet
The tools were already on the team's license list. Each one solved a part of this and left the expensive part alone.
Volume and speed, at a fidelity that is perfectly good for most categories.
In regulated payments every draft still arrived at review needing work, so the writing got faster and the queue did not move.
RejectedCopy produced inside a system the team already paid for, with no new tool to adopt.
The same fidelity problem, plus no awareness of per-platform character limits or of the firm's own legal and brand rules.
RejectedThe real accumulated knowledge, written by the people who actually understood the rules.
A document applied from memory, consulted after the writing, and out of date the week a platform revised its policy.
Became the schemaThe spreadsheet was the useful one, and its problem was its format. Turning it into structured records the generator could read while writing is the whole build.
Move the rulebooks in front of the writing
Review is expensive because it happens last. If the constraints are available while the copy is being written, most of what review used to catch never gets drafted.
So the policies became data instead of documents. Platform rules, company rules and compliance rules each live as structured records the generator reads, and the same records are what the audit pass scores against afterwards. One source, used twice.
CreativeOS is where two earlier builds ended up joined: the compliance reading from FinGuard and the platform-policy checking from AdGuard, now sitting inside the tool that does the writing.
Context in, angles first, copy second, policy throughout
A scan of your own landing page builds the product profile: what it offers, the funnel position, the audience and the claims the page already makes.
Generation produces distinct angles for the chosen platform and ad format first, so the variants argue different things rather than reword one idea.
Each angle expands into copy already shaped by that placement's specification, down to the headline and body character counts.
Every line is scored against platform policy, company policy and compliance rules, with the rule ID that fired attached to the finding.
Several models split the work. A control plane holds the system prompts and the tools each agent may reach, so changing behavior is a governed change instead of an edit inside a prompt string.
Compliance edits the policy, and the generator obeys it the same day
The people accountable for the rules maintain them directly. A compliance officer or marketing manager writes a company policy in the product, sets its severity, and chooses what happens when copy trips it: rewrite, warn, escalate or block. Legal reads the same records.
The platform side is a country-aware knowledge base rather than a banned-words list. Rules carry traceable IDs and source links, split into a global baseline and country-specific additions, alongside each placement's creative specification. When a finding appears, it says which rule and points at where that rule came from.
A person still signs off at the end. The intent is that they receive drafts which already respect the rules, so the review becomes a decision and not a repair job. Nobody outside me has run it, so that is the design, not a measured result.
Compliance owns one screen, and the generator reads it while it writes
Campaign-first generation: pick the platform and ad format, get angle-led copy back.
Saved jobs with their angles kept, so a campaign can be reopened and iterated instead of rebuilt.
The validation pass, reporting findings against the rule that produced each one.
The company policy engine and the country-aware platform knowledge base.
The product knowledge library, built by scanning the pages the ads will point at.
Four things a chat window leaves you to do by hand
Any model will write you an ad. The work that eats the afternoon happens after that draft exists, and all four pieces of it are mechanical enough to be owned by the tool.
It reads your own pages to learn the tone before it writes a line, so the draft arrives in the company's voice instead of a house style you then have to edit out.
Angles are stored against the campaign. Ask for more and it pushes into territory the campaign has not used, which is the difference between testing and repeating.
Counted with spaces, per field, per platform. A 27 of 30 headline is a headline you can paste; a 34-character one is a rewrite you find out about in the ads manager.
Platform policy and company policy shape the line as it is produced, with the reason attached, so the compliance pass stops being a separate round trip.
Coverage is four platforms with their formats built in: Google (Search, PMax, Demand Gen), Meta (Feed, Stories, Reels, Carousel), LinkedIn (sponsored content, lead gen) and Bing (Search, Audience, Shopping). The company's brand, legal and compliance rules sit as a fifth layer over all four. The audit path also runs backwards, so existing copy can be pasted in and checked against the same rules before it goes live.
One thing the product refuses to claim: it does not guarantee platform approval, because no tool can. What it lowers is avoidable risk, and where a line is genuinely a judgment call it says so and asks for a human. It is built for performance marketers, growth leads and marketing ops, at the point where drafting ends and approvals begin.
Two models with different jobs, and the rulebooks as data underneath both
Application
ReactThe five-surface workspace.
TypeScriptIncluding the policy-rule types, so a malformed rule fails at build.
ViteBuild tooling.
TailwindThe design layer.
Models
Gemini 2.5 FlashAngle generation and the per-platform copy pass, where speed matters more than depth.
DeepSeekThe policy audit pass, which reads each line against the matched rules and writes the reason.
Knowledge
Policy knowledge baseCountry-aware platform rules with traceable IDs and source links, stored as records rather than prompt text. Company policy engineThe firm’s own rules with a severity and an enforcement action per entry. Product knowledge libraryBuilt by scanning the landing pages the ads point at.Delivery
VercelHosting and the generation endpoints.
Keeping the rulebooks as structured records rather than prompt text is what lets the same source drive the writing pass and score the audit afterwards. One source, used twice.
Want this kind of tooling on your team?
Nine systems shipped across compliance, reporting, intelligence and content.