Last week we released V1.0.0 of our XenForo add-on to complement the new Relevio API "Coordinated Spam" detection. The add-on maintains coordinated spam statistics and provides new administrator tools to facilitate the detection and dismantling of the most legitimate looking agentic coordinated spam rings. 

About Coordinated Spam

Coordinated spam refers to a pattern where one user posts a question or engineers a post that invites a product recommendation. Then a subsequent user responds with an endorsement, recommendation, or promotion of a product, service, website.

The users act in a coordinated way in order to create authentic sets of posts that are in fact spam. It becomes obvious that two or more users are acting in this way when they start doing this with some frequency and a pattern evolves.

Modern AI agents have allowed the process of posting spam to be completely automated, resulting in a horribly large number of illegitimate posts for administrators to sift through. This is compounded by the agents posting legitimate looking posts and replies around the spam to dilute the spam below detectable thresholds or to elevate the account’s trust score before starting to spam.

Relevio does the hard part of this analysis: detecting what might or might not be coordinated spam and who might or might not be implicated in the spam, saving moderators from the significant amounts of time spent sifting through records. The XenForo add-on then gives moderators the tools needed to analyse the results and make informed decisions. 

The Relevio API has a new "Coordinated Spam" detection option. 

Since relevio is given the context of a comment or reply, the system is able use this to ascertain whether the relationship between the comment and the original post or another message in the reply chain is likely to be coordinated spam. 

The API now returns a "coordinatedSpam" attribute with the result of the risk assessment. Output values are "none", "low", "medium" and "high" . You can use this to tag up replies in your database and trigger workflows to suspend users when thresholds are met. Alternatively you can tailor your rulesets to always reject posts above a certain risk level. 

We are pleased to announce that we have extended our Microsoft, Facebook and Google logins to directly support Organisational accounts.  

By default Microsoft, Facebook and Google logins create personal accounts, but users are now given the opportunity to create an organisation. Both the personal account and the organisation account are then linked to the login. Users can switch between the personal account and organisational account.

This is part of our move to more open and flexible account management and a frictionless registration process. 

Following hard work by our research and development team we are pleased to announce the following:

•    A reduction in nominal text moderation time from 15-20 seconds to 1-2 seconds without any loss of accuracy in detection of rule violations or loss of sensitivity with multi-model coherence (relating images to text). 

 •    New Internal model fail-over semantics that mean Relevio now falls back on backup LLMs should our primary LLM fault. This in turn means the system is much more robust. 

•    A reduction in processing unit cost from 3p to 1p per unit. 

We are pleased to announce the release of our add-on for XenForo. This add-on enables XenForo users to benefit from all the Rule‑Driven Semantic Moderation features of Relevio, including:

•	Moderation before submission​

As with SmartWall, the XenForo integration uses our unique moderation before submission model, where moderation is invoked from the user interface before content ever reaches your server.

•	Context‑aware by design​

Every check includes context (the related thread and prior reply chain). Relevio understands where a new post sits in the conversation, so it can enforce relevance and keep threads coherent.

•	Multimodal coherence​

The XenForo integration checks that images, attachments and text actually belong together, evaluating them as a single semantic unit. This prevents users from pairing misleading images with unrelated narratives and keeps your platform coherent, trustworthy, and harder to exploit.

•	Cryptographically verifiable decisions​

Every approved submission is signed with an HMAC that binds the content, images, ruleset, and context together with your private key. The XenForo backend only accepts trusted, tamper‑proof posts.

•	Instant feedback for users​

The XenForo integration presents users with clear, structured explanations and actionable suggestions when quality checking fails. This reduces the irritation and distrust people feel when their content is rejected by a black‑box system. Users get transparent guidance that helps them fix issues quickly and stay engaged.

•	Multiple rulesets​

The XenForo integration Relevio allows you to define multiple rulesets, with different rules for new posts, replies, and across different forums / nodes. This allows you to keep individual forums focussed on particular topics. Rulesets are managed from your relevio.ai account.

•	Fail safe​

The XenForo add-on has a fail safe design. If the main Relevio service is unavailable or faults, then posts are automatically sent to the normal moderation queue. This ensures that your system is never blocked from receiving new posts.

•	Easy to configure​

All you need is a relevio.ai account. Simply install the add-on, enter your account id and private key in the add-on settings and you are ready to go.

•	Bypass permission​

Grant user groups permission to bypass Relevio moderation and allow your trusted users, administrators and moderators to post content without constraint.

•	Auditing and statistics​

Requests to Relevio moderation are fully audited and a range of statistics reports are available for analysing usage, costs, rule failures, etc. 

Datawing is pleased to introduce Relevio, a novel automated content moderation system for websites and web applications. 

Relevio is a new class of moderation engine employing Rule‑Driven Semantic Moderation, which uses the full power of large language models (LLM) to produce a unique context‑aware, rule‑driven moderation engine that enables full and reliable autonomous story boards and forums. This is very different from the established method of Category‑Based Classifier Moderation employed by systems such as Hive or Tisane.

There are two main products:

Relevio API 

A stand alone Pay-as-you-go service for application developers who wish to leverage the power of Rule‑Driven Semantic Moderation in their own websites and products.

Smart Wall 

A simple hosted story board service delivered on a subscription model. Smart Wall can be configured as a complete content management micro website or embedded in an existing website uising our embedded components.