Install Jentic One Beta
Jentic One is a self-hosted execution layer for AI agents. It lets your agent call the Prembly API, or any other public or private API you need. You set the rules, the agent never sees your credentials, and every call is logged.
Two steps, two machines. Install the instance in a safe environment, then register your agent from wherever it runs.
Step 1: Jentic One Host machine
# On the machine that will host your Jentic One instance:
curl -fsSL "https://jentic.com/install.sh?src=apis&api=%2Fapis%2Fprembly.com%2Fprembly" | shStep 2: Agent machine
# On the machine where your agent runs (keep this separate from the instance):
curl -fsSL "https://jentic.com/install.sh?src=apis&api=%2Fapis%2Fprembly.com%2Fprembly" | sh
jentic register # connects your agent to your Jentic One instanceJentic One is in public beta. The setup above keeps your agent separate from the instance, which is what you want before using real credentials: an agent running as the same OS user as Jentic One can read its stored keys directly. Just evaluating? A single local install is fine to start. See the secure deployment guide for the tiers.
What an agent can do with Prembly API.
Verify government-issued identity documents with face comparison in a single call
Screen individuals against global PEP and sanctions watchlists
Detect facial liveness to prevent spoofing during biometric onboarding
Run background checks on candidates with configurable verification packages
Monitor transactions for suspicious patterns and flag potential fraud
GET STARTED
Search company registrations by person name or registration number
Submit and track fraud reports linked to verified identities
Patterns agents use Prembly API for, with concrete tasks.
★ Customer Onboarding KYC
Verify new customer identities during account registration using government-issued ID documents combined with biometric face matching. Prembly processes the document image, extracts data fields, compares the document photo against a live selfie, and returns a verification verdict. This covers markets across Africa where traditional credit bureau checks are unavailable, enabling fintech and banking products to onboard users in minutes rather than days.
Submit a Nigerian national ID card image and a selfie to the document-verification-face endpoint and confirm the verification status is approved
PEP and Sanctions Screening
Screen individuals and entities against politically exposed persons lists and international sanctions databases before processing transactions or establishing business relationships. The Prembly PEP/sanctions endpoint accepts a person's name and returns matching records with confidence scores, enabling compliance teams to make informed decisions. Screening runs in real time and supports ongoing monitoring for changes in status.
Submit a full name to the pep-sanction endpoint and parse the response to determine if any matches exceed a 0.8 confidence threshold
Employee Background Checks
Conduct pre-employment background verification by creating candidates, attaching verification packages, and tracking results through completion. Prembly supports configurable packages that can include ID verification, criminal record checks, and education verification. The candidate lifecycle tracks from submission through completion with status polling or reinitiation if additional information is needed.
Create a new candidate with personal details, assign a standard verification package, and poll the candidate status until verification completes
AI Agent Identity Verification Pipeline
AI agents use Prembly through Jentic to build automated identity verification pipelines that combine document scanning, face comparison, and liveness detection without manual integration work. The agent searches Jentic for identity verification operations, loads the required schemas, and executes multi-step verification flows including document upload, biometric matching, and status checking in a single orchestrated sequence.
Search Jentic for 'verify identity document with face match', load the document-verification-face operation schema, and execute with a test document image and selfie
32 endpoints — prembly provides identity verification and fraud prevention services focused on emerging markets across africa and beyond.
METHOD
PATH
DESCRIPTION
/document-verification
Verify an identity document
/document-verification-face
Verify document with face comparison
/face-liveliness
Detect liveness in a facial image
/pep-sanction
Screen against PEP and sanctions lists
/face-comparison
Compare two facial images
/candidates
Create a background check candidate
/verification-status
Check status of a verification request
/tm-transaction-monitoring
Monitor a transaction for fraud
/document-verification
Verify an identity document
/document-verification-face
Verify document with face comparison
/face-liveliness
Detect liveness in a facial image
/pep-sanction
Screen against PEP and sanctions lists
/face-comparison
Compare two facial images
/candidates
Create a background check candidate
/verification-status
Check status of a verification request
/tm-transaction-monitoring
Monitor a transaction for fraud
What agents get from Jentic-routed access to this vendor.
Setup
Wiring the Prembly API by hand means putting your secret key in the Authorization header against api.prembly.com and building your own multipart uploads for document and face-verification calls. Through Jentic you install once, import the Prembly API from the API Directory, store the API key once, and your agent calls it.
Permission scoping
Prembly takes the document images and identity details in the request body rather than as a path resource, so scoping is by operation: you limit the agent to the operations it needs, such as document verification or a sanctions check. Face liveliness, face comparison, or transaction monitoring are included only if you add those operations.
Credential isolation
Your Prembly secret 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.
Intent-based discovery
Agents search Jentic by intent such as 'verify an identity document with a face match' or 'run a PEP and sanctions screen', and Jentic returns the matching Prembly operation with its input schema so the agent calls the right endpoint without browsing the reference docs.
Alternatives and complements available in the Jentic catalogue.
Stripe API
Payment processing that pairs with identity verification for compliant onboarding
Use Stripe alongside Prembly when you need to verify identity before enabling payment processing capabilities.
Specific to using Prembly API through Jentic.
What authentication does the Prembly API use?
The Prembly API uses API key authentication passed in the Authorization header. Through Jentic, your API key is stored encrypted in your Jentic One instance and agents receive scoped access tokens, so the raw secret key never enters the agent context.
Can I verify identity documents with face matching in a single request?
Yes. The POST /document-verification-face endpoint accepts both an identity document image and a selfie, performs document data extraction and facial comparison together, and returns a combined verification result with confidence scores.
What are the rate limits for the Prembly API?
Rate limits depend on your Prembly subscription tier. You can check your current usage capacity via the GET /wallet-balance endpoint which returns your remaining verification credits. Higher-tier plans include increased throughput and priority processing.
How do I run a PEP and sanctions screening through Jentic?
Search Jentic for 'screen person against sanctions list', load the pep-sanction operation schema, and execute with the person's full name. The response includes matched records with confidence scores. Install the SDK with pip install jentic and authenticate with your JENTIC_AGENT_API_KEY.
Which countries does the Prembly API support for identity verification?
The GET /countries endpoint returns the full list of supported countries. Prembly focuses on African and emerging markets including Nigeria, Kenya, Ghana, South Africa, and others, with document types varying by country. The GET /check-types endpoint lists available verification methods per country.
Can I track the status of an ongoing background check?
Yes. After creating a candidate via POST /candidates, poll GET /candidates/{id} to check the verification progress. If a check stalls or needs re-submission, use POST /candidates/{id}/reinitiate to restart the process with updated information.
Can I limit what my agent is allowed to do with the Prembly API?
Yes. Because you run Jentic One yourself, your own rules decide which Prembly operations and credentials the agent may use. Prembly takes document images and identity details in the request body rather than as a path resource, so scoping is by operation: you can restrict the agent to only the calls it needs, such as document verification or a PEP and sanctions screen. Operations like face liveliness, face comparison, or transaction monitoring are available only if you explicitly add them.
For Agents
Verify identities with document checks, biometric face matching, liveness detection, and PEP/sanctions screening across African and emerging markets.
Use for: I need to verify a customer's identity document, I want to screen a person against PEP and sanctions lists, Check whether a facial image passes liveness detection, I need to run a background check on a new hire
Not supported: Does not handle payment processing, credit scoring, or account management - use for identity verification and fraud screening only.
Prembly provides identity verification and fraud prevention services focused on emerging markets across Africa and beyond. The API supports document verification, biometric face matching, liveness detection, PEP and sanctions screening, company searches, transaction monitoring, and background checks across 32 endpoints. It covers the full KYC lifecycle from initial ID document scanning through ongoing fraud monitoring.
This API is usable in Jentic One now. Its AI-readiness score against Jentic's framework shows where it stands today and where improvements would make it even easier for agents to use.
Base layer of spec validity and structural soundness.
Aggregated quality score from linter diagnostics, weighted by severity.
Percentage of `$ref` references that resolve successfully.
Checks whether the API description parses successfully and conforms to its declared specification (e.g., OpenAPI).
Structural correctness score based on schema issues using logarithmic dampening.
Clarity, completeness, and ingestion readiness for developers and tooling.
How richly the API is illustrated with examples.
Percentage of examples that conform to their schemas.
Percentage of operations with complete response definitions (success, client error, server error).
Health of API ingestion, bundling, and resolution within Jentic pipelines.
Semantic breadth, depth, and agent comprehension for AI systems.
Coverage of descriptions across API elements.
Coverage of RFC 9457 Problem Details for error responses.
Coverage, uniqueness, and casing consistency of operationIds for AI inference.
Coverage of summaries across operations/tags/info.
Functional utility, complexity comfort, and AI orchestration readiness.
Agent comfort level based on API operational and structural complexity.
Trust, risk posture, and security compliance.
Average quality of security schemes based on authentication method strength (weakest link for OAuth2).
Findability, semantic richness, and reasoning readiness.
Clarity and depth of descriptions across API elements.
Score it yourself
Every API in the directory is allowlisted, so you can re-score it with no key required.
npx @jentic/api-scorecard-cli score <openapi-url>