Chat: Go beyond keyword filters with AI detection and triage
We all have a breaking point — GGWP looks at the whole conversation to determine who the instigators were and the relationships of players involved
GGWP is built by gamers, for gamers. We understand and constantly update our models with the nuances of gaming jargon
Know each player’s holistic contribution to your community over time and across contexts (Chat, Gameplay, Discord) to sanction and reward with confidence
Automate moderation out of the box, with prioritized incidents for your moderators to review in our easy-to-use dashboard
Everything depends on context. A playful joke made to a friend lands very differently when said to a stranger in a ranked match. That is why GGWP takes into account the full context of the game and conversation – e.g. the mood of the conversation and each player up until the incident, whether the game was ranked, whether the players chose to re-queue together. This comprehensive view allows us to confidently assess each impact’s severity and make sure penalties are fair.
Know each player’s holistic contribution to your community – across time and contexts. Our player reputations take into account the positive, neutral, and negative messages and actions taken by each player and auto-detected by our AI, meaning that our reputations are truly holistic and comprehensive. With a complete player 360° view, you can deeply understand your community and moderate players with confidence.
GGWP is built by gamers, for gamers. We understand and constantly update our models with the nuances of gaming jargon.
We know that “nice job” means something different when you just defeated a boss than when said to a new player when a team is losing, and GGWP takes that context and implicit meaning into account when interpreting what is an act of toxicity or an act of encouragement.
GGWP uses our AI-based chat detections to auto-confirm verbal abuse reports, reducing the manual effort required for review. Our system cross-references reported incidents with the user’s chat history and behavioral patterns, providing a comprehensive view of the situation and supporting you in making informed moderation decisions.
Use GGWP to moderate the behavior of your audience globally. We have comprehensive language coverage and add new languages regularly, when we see an increase in volume or customer need. In short and hard-to-classify gaming messages, GGWP’s unique algorithms match players. Our current languages include Arabic, Chinese, English, French, German, Indonesian, Italian, Japanese, Korean, Portuguese, Polish, Russian, Spanish, Thai, Turkish and Vietnamese.
Integrate your chat into our game within minutes with our easy-to-use API.
Your team automatically gets access to our dashboard and auto-moderation features, with no configuration required.
When you send us additional information about player activity and match summaries, you get richer and deeper insights at no charge to you.
Our platform provides a gaming-specific solution that is designed to work well out of the box. However, we also know each game is unique. With GGWP, you can customize the sensitivity of our live filtering to match the tone of your game’s community, apply game-specific allowlists and blocklists, and pick either GGWP-provided or your own phrases to replace toxic messages if you choose to do so.
Understand your game’s aggregate community health, review incidents that occur with contextual information. View each player’s detailed history and see each incident in context using our smart, AI-powered moderation platform – included at no charge with your subscription.
GGWP enables you to moderate messages in the moment and take automated action to sanction players.
Our automated actions are based on a full AI-based review of that player’s history as well as the incident in question, much like a human moderator would do.
This means you can finally ensure that your community stays healthy with a >90% reduction in manual effort.
We accommodate that by default - our models are available by API across regions and our live filtering detections run in <20 ms.
We use probabilistic models and set different confidence thresholds depending on the detection type and application. For more critical and severe detections precision values range from 95-98%. For milder detections in more sensitive domains (eg: games for kids) we optimize for recall, with general values over 95%.
We are also constantly improving our models with a comprehensive QA process that includes manual labelling by our in-house team, incorporating customer feedback on individual incidents, tracking new terms that are starting to appear with more frequency, and adding language that is emerging in the gaming community.
Our scores take into account different sources of information and take a really long term view. They also take into account the confidence and severity of each incident to ensure that reputation impacts are fair and feel reliable for decision making to moderators and can be used by our AutoMod sanctioning system.
We think adversarially and assume that gamers using our platform will be trying to get by our system. This means we cover all the commonly used workaround like 1337speak, numbers, spaces, and more. We constantly update our models to provide the best defense and use domain expertise in addition to data science to proactively predict. When we are playing games and see workarounds being used, we immediately ask, “how can we add this to our systems?”
GGWP is committed to protecting the privacy and personal data of our customers. We understand the importance of complying with the General Data Protection Regulation (GDPR) and the California Consumer Privacy Act (CCPA) and have taken necessary steps to ensure that we are fully compliant with both regulations.
As a data processor, we respect and work with data controllers to ensure that their users' data is protected and processed in accordance with GDPR and CCPA regulations. We have implemented appropriate technical and organizational measures to safeguard personal data and comply with the data controller over a given user's right to be forgotten as well as the right for their customer to access their data.
We take our responsibility as a data processor seriously and have implemented strict policies and procedures to ensure that all personal data is processed lawfully, fairly, and transparently. Our team undergoes regular training to ensure that they are fully aware of their responsibilities under GDPR and CCPA.
We accommodate that by default - our models are available by API across regions and our live filtering detections run in <20 ms.