> For the complete documentation index, see [llms.txt](https://docs.lassomoderation.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.lassomoderation.com/lasso-moderation-overview.md). # Lasso Moderation Overview Lasso's moderation platform is easy to integrate. Below we describe the different parts of the platform, how they work and how they interact with your platform. If you are new to Lasso, start with [Key Concepts](/key-concepts.md) for an introduction to the terms used throughout these docs.

An overview of the flow through the platform

### Flow The flow through the platform works in 3 simple steps: 1. [Ingest content through the API](#lasso-api): your platform sends content (text, images, video and audio) and user information to Lasso through the Lasso API or one of our integrations. 2. [Automation](#automation): your moderation rules and AI Moderators automatically take action on incoming content and users. Actions are automatically relayed back to your platform by a webhook call. 3. [Human action](#human-action): not everything can be moderated automatically. Lasso provides an easy-to-use dashboard where your moderators review the content and users that automation flagged for a closer look. Human actions are relayed back to your platform by a webhook call. ### Lasso API Integrating with Lasso takes a few API endpoints and a webhook. #### Ingest content This is the main and most important API endpoint and is used to send content into the Lasso Moderation platform. All content immediately shows up in the dashboard and is automatically analyzed and checked against your moderation rules. There are two ways to send content: * **Post-moderation**: `POST /api/v1/content` returns immediately and the content is moderated in the background. Decisions arrive through your webhook. This is the standard setup. * **Pre-moderation**: `POST /api/v1/content/sync` waits for the automated checks and returns the decision in the response, for platforms where content only goes live after approval. Reference: If your platform is built on a service such as Stream, TalkJS, CometChat or PubNub, Lasso can also ingest content directly through an integration, without an API integration on your side. Contact us to set this up. #### Ingest users This endpoint can be used to update users' information in Lasso. This can be used if important information of a user changes without the user posting any new content. Information about the user can be used for customized moderation rules. Note: We care a lot about our and your user's privacy, so be careful sending personal identifiable information (PII) to our platform. Reference: #### User reports The user reporting endpoint should be called when your users report another user or a piece of content on your platform. These reports automatically show up in the dashboard and can also be used in custom moderation rules. Reference: #### Webhook Webhooks are used to communicate back to your platform. Any action (a rule, an AI Moderator or a human moderator) sends a webhook call to your platform with the new status of the content or user. For example, a rule could automatically remove images containing nudity; Lasso then makes a webhook call to your platform letting it know that this content should be removed. Every call is signed, so your platform can verify it came from Lasso. More information on how to implement the webhook can be found here: [Webhooks](/webhooks.md) #### Other API endpoints A full overview of all API endpoints can be found [here](https://api-reference.lassomoderation.com/). ### Automation #### AI analysis and classifiers Every incoming item is analyzed automatically: text receives AI scores for toxicity and related categories, images are scanned for unsafe content and for text they contain, and classifiers check content against policies specific to your platform. These signals do not take action by themselves; your rules and AI Moderators turn them into decisions, so you stay in control of the thresholds and the consequences. #### Custom moderation rules Custom moderation rules are a big part of Lasso's moderation platform. Rules are collections of conditions with a certain action. For example, flag (action) users that have signed up in the last 3 hours (condition) and have posted more content containing nudity (conditions). All rules can be fully customized to your platform. Every platform is different, so we believe every platform should be moderated in a different way. Rules can also be adjusted on the fly, no coding or deployments needed anymore. Incoming content and users will automatically be evaluated against your (updated) rules. Read more about [Custom Moderation Rules](/custom-moderation-rules.md) #### AI Moderators AI Moderators are AI members of your moderation team. An AI Moderator reads your written policy and judges content against it the way a human moderator would, explaining its reasoning with every decision. Depending on its configuration it takes action directly or leaves a recommendation for a human to confirm. The written policy can be adjusted on the fly, and you control which actions the AI Moderator may take and how decisive it is. ### Human Action Lasso provides an extensive dashboard where human moderators can easily moderate content and users. Human actions are relayed back to your platform by a webhook call. The main sections of the dashboard: * **Review**: work through flagged content and users in [review queues](/review-queues.md) * **Content** and **Users**: browse and search everything flowing through your platform * **Rules**, **Policies** and **Lists**: manage your automated moderation * **User Reports**: triage [reports](/user-reports.md) filed by your users * **Audit Logs**: every action and change in your workspace, by whom, and when * **Analytics**: insight into the health of your content, users and moderation * **Team**: manage your moderators and AI Moderators Each of these concepts is explained in more detail in [Key Concepts](/key-concepts.md).