canonical: https://jentic.com/apis/complyadvantage.com/complyadvantage # ComplyAdvantage API Jentic publishes the only available OpenAPI specification for ComplyAdvantage API, keeping it validated and agent-ready. The ComplyAdvantage API automates anti-money-laundering screening against sanctions, politically exposed persons, watchlists, and adverse media. It is built around named search jobs that return matched entities, supports ongoing monitoring of those searches, and lets compliance teams acknowledge alerts, comment on cases, and tag results. Regional endpoints are available in the EU, US, and APAC for data-residency requirements. ## For AI agents Run AML searches against sanctions, PEP, watchlist, and adverse-media data, then monitor each search for new hits and track case decisions through entities, comments, and tags. ## Scope Does not handle document verification, biometric checks, or transaction monitoring - use for sanctions, PEP, watchlist, and adverse-media screening only. ## Capabilities - Run an AML search against sanctions, PEP, watchlist, and adverse-media datasets for a named individual or entity - Retrieve detailed match data and source-level evidence for a search result - Enable ongoing monitoring on a search so new hits trigger alerts - Acknowledge monitor alerts to mark them reviewed - Add comments to a search to record investigator notes and decisions - Apply or remove tags on a search to drive case workflow states - Manage user accounts that own searches and case actions ## Use cases ### Customer Onboarding AML Screening Screen every new customer against sanctions, PEP, watchlist, and adverse-media data at the point of onboarding. The /searches endpoint creates a named search and returns matches with source evidence; investigators then use comments and tags on the search to record their decision. Fintech, banking, and crypto onboarding flows use this to satisfy KYC and AML obligations before account opening. Example prompt: Create a search named 'Acme Trading Ltd' against sanctions and PEP datasets, fetch the matched entities, and tag the search 'review' if any matches are returned ### Ongoing Customer Monitoring Keep onboarded customers under continuous AML watch so changes in sanctions, PEP, or adverse-media status are detected without re-running screening manually. Calling /searches/{id}/monitors enables monitoring on a search, and the acknowledge endpoint lets investigators clear alerts as they triage them. This supports the periodic-review obligations under FATF, FCA, and FinCEN guidance. Example prompt: Enable monitoring on search id 12345, then list all unacknowledged monitor alerts created in the last 7 days ### Investigator Case Workflow Drive a small case-management workflow on top of the search records. Investigators can attach comments via /searches/{id}/comments, apply tags such as 'pending', 'cleared', or 'sar-filed' via /searches/{id}/tags/{tagName}, and inspect details via /searches/{id}/details. Compliance teams use this to keep audit trails inside ComplyAdvantage rather than exporting to a separate ticketing system. Example prompt: For each search tagged 'pending' for more than 5 days, post an investigator comment 'reminder: review pending' and list the search ids ### Agent-Driven AML Triage via Jentic Let an AI agent triage AML alerts by running the appropriate search, summarizing match evidence, and applying the right tag based on a configurable rule. Through Jentic the agent searches by intent, loads the schema for the relevant ComplyAdvantage operation, and executes the call without the developer wiring auth or pagination. This compresses the manual triage step that compliance teams typically carry. Example prompt: Given a new customer 'Maria Hernandez', create a search, summarize any matched entities in two lines, and tag the search 'auto-cleared' if zero matches ## Key endpoints | Method | Path | Description | | --- | --- | --- | | POST | /searches | Create an AML search against selected datasets | | GET | /searches/{id} | Retrieve a search and its summary | | GET | /searches/{id}/details | Retrieve detailed match evidence for a search | | GET | /searches/{id}/entities | List matched entities for a search | | PATCH | /searches/{id}/monitors | Enable or disable ongoing monitoring on a search | | PATCH | /searches/{id}/monitor/acknowledge | Acknowledge monitor alerts | | POST | /searches/{id}/comments | Add an investigator comment to a search | | PUT | /searches/{id}/tags/{tagName} | Apply a tag to a search | ## Key resources - **Users** — User accounts that own searches and decisions - **Searches** — AML searches against sanctions, PEP, watchlist, and adverse-media data - **Search details and entities** — Full match evidence and matched entity records for a search - **Monitors** — Ongoing monitoring subscriptions on a search and alert acknowledgement - **Comments** — Investigator notes attached to a search - **Tags** — Workflow tags applied to a search ## Why Jentic - **Setup:** Wiring ComplyAdvantage by hand means learning its API key scheme, building sanctions and PEP screening searches, and tracking monitor and match state yourself. Through Jentic you install once, import ComplyAdvantage from the API Directory, store the key once, and your agent calls it. - **Permission scoping:** ComplyAdvantage puts the search id in the URL path (/searches/{id}, /searches/{id}/entities), so a rule can pin your agent to reading a specific screening search. You choose the operations it may call, so you can allow creating and reading searches while leaving monitor changes or tag edits out unless you add them. - **Credential handling:** Your ComplyAdvantage API key is stored once, encrypted, by your own Jentic One instance and injected at execution time. It never enters the agent's prompt, logs, or context. - **Discovery method:** Agents search Jentic by intent such as 'screen a name against sanctions lists' or 'check a search for PEP matches', and Jentic returns the matching ComplyAdvantage operation with its input schema so the agent calls the right endpoint without browsing the reference docs. ## Related APIs - **OpenSanctions** — Open dataset of sanctions, PEP, and watchlist entries with a free tier - **Onfido** — Document and biometric identity verification - **Persona** — Configurable identity verification and KYC orchestration ## FAQ ### Why is there no official OpenAPI spec for ComplyAdvantage API? ComplyAdvantage does not publish an OpenAPI specification. Jentic generates and maintains this spec so that AI agents and developers can call ComplyAdvantage API via structured tooling. It is validated against the live API and kept up to date. Get started with Jentic One, the self-hosted execution layer. ### What authentication does the ComplyAdvantage API use? The API uses an API key passed in the Authorization header in the form 'Token YOUR_API_KEY'. Through Jentic the key is stored encrypted in the vault and injected at execution time, so the raw key never enters the agent's prompt or logs. All requests must be made over HTTPS. ### Can I enable ongoing monitoring on an AML search? Yes. After creating a search via POST /searches, call PATCH /searches/{id}/monitors to enable monitoring on that search. New matches generate alerts that you clear with PATCH /searches/{id}/monitor/acknowledge. ### What are the rate limits for the ComplyAdvantage API? ComplyAdvantage applies tenant-specific rate limits, commonly 100 requests per second per API key with bulk-search throttling. The exact limit depends on your contract; agents should add backoff on HTTP 429 and Jentic surfaces these as structured errors rather than retrying silently. ### How do I run a sanctions search through Jentic? Run the Jentic search query 'run an AML sanctions check', load the returned operation (POST /searches), and execute it with the search term and dataset filters. Then call GET /searches/{id}/entities to fetch the matched entities. ### Which regions can I host my data in? ComplyAdvantage offers three regional endpoints: api.complyadvantage.com (EU), api.us.complyadvantage.com (US), and api.ap.complyadvantage.com (APAC). Pick the endpoint that matches your data-residency obligations and use the same one consistently. ### Can I limit what my agent is allowed to do with the ComplyAdvantage API? Yes. Because you run Jentic One yourself, your own rules decide which ComplyAdvantage operations and which stored API key the agent may use. ComplyAdvantage puts the search id in the URL path, as in GET /searches/{id} and GET /searches/{id}/entities, so a rule can pin the agent to reading one specific screening search. You can allow it to create and read searches while leaving PATCH /searches/{id}/monitors and the tag edits under PUT /searches/{id}/tags/{tagName} out unless you add them.