AuditSocials: Platform Policy and Enforcement Intelligence
AuditSocials is our own product. It tracks the advertising and content policies of 8 social and ad platforms. It also tracks live enforcement data from the EU DSA Transparency Database and moves by regulators. It turns all of this into one feed, ranked for your industry. The same engine is available as a REST API and an MCP server (a way for AI assistants to use it), so content can be checked before it is published.
- Project
- Data platform
- Our role
- Own product, end-to-end
- Platform
- Next.js
- Country
- Global
- Year
- 2026
The challenge
Rules change quietly
Meta, TikTok, Google Ads, LinkedIn, YouTube, X, Snapchat and Pinterest all change their policy pages without much notice. Advertisers, agencies and creators usually find out when an ad is rejected or an account is restricted, not when the rule changes.
Too many sources, no ranking
Policy pages, the EU's daily moderation data and actions by regulators such as the FTC, Ofcom, eSafety and the SEC each tell part of the story. Reading all of them is a full-time job, and most of it does not apply to any one business.
AI-written content needs a check
Products that write ads and social posts with AI publish a lot of content, often without knowing what each platform allows right now. They needed a way to flag policy risk before their users publish, with the rule behind every flag.
Our approach
Three streams, one ranked feed
Our crawler reads the policy pages of all 8 platforms, and AI summarises every change. Each summary is marked as editor-reviewed or auto-checked against the source. Each change gets a severity score and is linked to the industries it affects. Spikes in enforcement from the EU DSA Transparency Database and early signals from regulators sit in the same feed.
Reference content around the feed
A guide per platform, 15 industry pages, a rejection library, a platform comparison, a glossary and 19 regional law pages give visitors the context behind each alert. A blog covers each policy change as it happens. Free tools such as a disclosure checker and shadowban detectors bring people in.
Compliance checks as an API and an MCP server
The same policy engine is available as a REST endpoint. You send it content, a platform and a region. It returns a risk level, the policy behind each flag and a suggested fix. An MCP server gives AI assistants four tools: check content, track policy changes, measure enforcement and follow regulator moves. Clients connect by signing in, or with an API key for automated setups with no screen.
Screens
Inside AuditSocials
How we delivered
From first brief to running in production
-
01
DataPolicy crawling
We read each platform's policy pages automatically, summarise every change and link it to the industries it affects.
8 platformsAI summariesSeverity scoring -
02
Enforcement & regulators
DataWe pull daily moderation data from the EU DSA Transparency Database and track regulator actions as early warning signs.
EU DSA databaseEnforcement indexEarly signals -
03
Reference library
ContentWe published platform guides, industry pages, a rejection library, a glossary and regional law pages around the feed.
Platform guides15 industries19 regional law pages -
04
API & MCP server
IntegrationWe made the policy engine available as a check before publishing, over REST, and as an MCP server with four tools.
REST APIMCPnpx package
Results
What is running today
A live policy-tracking product
AuditSocials runs on auditsocials.com with a policy tracker, an enforcement index per platform and an early-signals feed. All of them run on the same daily data. Every summary is labelled as editor-reviewed or auto-checked against its source. The DSA data carries its CC BY 4.0 attribution.
Built for several audiences
Solution pages speak to enterprise compliance teams, agencies, brand and performance marketers, researchers and press, law firms and creators. Each one leads into the same feed, filtered to their sector.
A check AI tools can call
Developers can try the compliance check without signing up, then use a free tier of API credits. The MCP server works with Claude, ChatGPT, Cursor and other MCP clients. It is also published as an npx package.
More work
Other things we built and run
Estimonia
Estimonia is our own product. Upload photos of an antique, watch or piece of jewellery and get a USD value range, a confidence score and a written explanation. We built it and we run it. It has a Laravel 12 API that analyses photos with AI in the background, a web scanner and an auction house directory.
Senfoni Koçluk
An Istanbul student-coaching practice ran on WhatsApp, spreadsheets and memory. We built one Laravel platform that covers the public site and free exam tools, portals for students and parents, and the coach's back office: exams, schedules, sessions and payments.
SchoolVita
SchoolVita is our own product: a directory of private and international schools in 20 cities where families relocate. Parents compare estimated fees and curricula, then send an enquiry to the schools they choose. Schools can claim their listing and receive those enquiries.
