> For the complete documentation index, see [llms.txt](https://detected.gitbook.io/detected-api-docs/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://detected.gitbook.io/detected-api-docs/about-detected.md). # About Detected Detected: top-level glossary ## What we are * **Detected**: The "Trust Platform". An all-in-one platform that helps organisations establish and maintain trust with any business or individual, anywhere in the world. * **KYB (Know Your Business)**: Verifying companies: registry data, ownership, directors, documents. * **KYC (Know Your Customer)**: Verifying individuals: ID documents, biometrics, personal data cross-checks. * **Trust decision**: The core question the platform answers: "Can we trust this business or individual?" ## What we do * **Onboarding**: Configurable, multi-language, multi-device customer journeys that collect the right information per market and business type. * **Verification**: Entity search and validation, global registry integration, UBO discovery, corporate hierarchies, ID and document checks. * **Screening & due diligence**: Sanctions/PEP, watchlists, enhanced due diligence (EDD) for high-risk entities. * **Decisioning**: Automated risk indicators, policy-driven decisions, fraud detection. * **Monitoring**: Continuous entity monitoring after onboarding. * **Case management**: One connected workspace where the compliance team sees information, checks and decisions together. * **Reporting & integration**: Reporting plus integrations with customers' own systems. * **AI-assisted compliance**: Opt-in AI that validates submissions, prepares case profiles for human review, and exposes platform data to customers' own agents via MCP. ## Key platform concepts ### Customer-facing * **Branded customer journeys**: Customers go through onboarding under the client's brand, using a white-labelled hosted UI. Partners can offer the same journeys under their own brand ("Powered by Detected"). * **Brand Hub**: Each brand gets its own look and its own selection of onboarding modules. Every brand is still managed from one central compliance environment. * **Flexible onboarding modules**: The building blocks of a journey (company information, directors, ownership, document upload, ID verification and so on). Clients choose which to include and how they're sequenced. * **Customisable journeys**: Journeys vary by location, business type and risk level. The rules are configured in Detected rather than hard-coded. * **Customer experience features**: Save-and-return across devices, multi-user collaboration, an onboarding checklist with guidance, pre-populated key individuals, and automatic localisation of language and character sets. ### Verification and data * **Global registry integration**: Entity search and validation against official company registries, with the option to pull registry documents directly. * **UBO discovery & corporate hierarchies**: Uncovering ultimate beneficial owners and mapping ownership structures across layers of entities. * **Data Summary**: A side-by-side view of what the customer declared versus what registries and data providers verified. * **Document collection & authentication**: Collecting documents, then checking them via OCR, translation and authenticity checks. * **Automated linking**: Connecting individuals and entities across the record so analysts see the relationships. ### AI AI is integrated throughout the platform. Every feature is opt-in and fully configurable. * **Support, don't replace**: AI is advisory. It surfaces insights, not verdicts, and human sign-off is enforced at every decision point. * **Transparent by default**: AI reasoning is always explainable, so analysts can see why a recommendation was made, challenge it, and support audit. * **Realtime onboarding validation**: AI assistants catch issues as customers submit, meaning fewer round-trips and cleaner data. * **Native agentic workflows**: A managed compliance agent works the case and prepares a full profile before a human reviews it. * **External agentic integration**: An MCP Server connects customers' own agents to Detected data and capabilities, with full auditability. * **AI safeguards**: Guardrails on inputs and outputs, prompt injection protection, hallucination controls, continuous monitoring and cost controls. * **AI audit trails**: Every AI interaction is logged (what was asked, what was returned, who acted) to support regulatory review. ### Platform architecture * **Configurability**: The platform is built around the client's policy, not the other way round. Journeys, data, decisions and monitoring are configured per country, industry and risk appetite, and clients go live in weeks. * **Jurisdictional flexibility**: The same platform handles market-specific requirements, such as different registries, ID types and tax identifiers by country. * **Orchestration engine**: Routes, validates and sequences outputs from multiple data providers within a workflow, so clients get the best provider per category under one set of policies. * **Platform partners**: Providers that live natively inside the platform, e.g. ComplyAdvantage, Dun & Bradstreet, LSEG, Moody's, Trulioo, GBG, OpenCorporates, Kyckr, Creditsafe, Resistant AI and Global Database. Infrastructure partners include AWS and Google Maps. ### Team-facing * **Case management workspace**: One current view per customer, covering information, checks, evidence and decisions, so reviewers aren't stitching together separate tools. * **Ongoing monitoring**: Trust doesn't stop at onboarding. Entities are monitored continuously, with high-risk cases escalated to EDD. --- # Agent Instructions This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com. ## Querying This Documentation If you need additional information that is not directly available in this page, you can query the documentation by asking a question. Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters: ``` GET https://detected.gitbook.io/detected-api-docs/about-detected.md?ask=&goal= ``` `ask` is the immediate question: it should be specific, self-contained, and written in natural language. `goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case. The response will contain a direct answer to the question and relevant excerpts and sources from the documentation. Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.