Install Jentic One Beta
Jentic One is a self-hosted execution layer for AI agents. It lets your agent call the RouteOne 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%2Frouteone.com%2Frouteone" | 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%2Frouteone.com%2Frouteone" | 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 RouteOne API.
Submit a buyer's credit application to lenders
Check the approval decision and status of a submitted application
List participating dealers on the RouteOne network
List available lenders for indirect financing
Route a financing request to the lenders a dealer works with
GET STARTED
Patterns agents use RouteOne API for, with concrete tasks.
★ AI Agent Integration via Jentic
AI agents discover and call RouteOne API endpoints through Jentic without managing credentials directly. An agent searches for the required operation by intent, receives the matching endpoint schema, and executes the call with Jentic-managed authentication. This lets a dealer's deal-building assistant submit a credit application and poll its decision programmatically instead of a person re-keying it into a separate lender portal.
Search Jentic for 'submit credit application', load the operation schema, and execute POST /applications with Jentic-managed credentials
Close the Financing Step of a Car Deal
Submit a buyer's credit application to indirect lenders and surface the approval decision inside the dealer's own workflow. The dealer sends the application through POST /applications and polls GET /applications/{applicationId} for an approved, conditioned, or declined decision, keeping the customer at the desk instead of waiting on a callback. This turns the most friction-heavy step of the sale into an automated flow.
Call POST /applications to submit the buyer's credit application, then poll GET /applications/{applicationId} until a lender decision is returned
Power a Lender Marketplace Feature
Show which lenders are available and route a financing request to the right ones. An agent calls GET /lenders to retrieve participating lenders and GET /dealers to confirm dealer enrolment, then submits the application to the lenders that fit the buyer's profile. This turns a manual lender handoff into a working, automated marketplace.
Call GET /lenders to retrieve available lenders, then submit the application to the matching lenders via POST /applications
4 endpoints — submit automotive credit applications to lenders and track their approval decisions.
METHOD
PATH
DESCRIPTION
/applications
Submit credit application
/applications/{applicationId}
Get application status
/dealers
List dealers
/lenders
List lenders
/applications
Submit credit application
/applications/{applicationId}
Get application status
/dealers
List dealers
/lenders
List lenders
What agents get from Jentic-routed access to this vendor.
Setup
Wiring RouteOne by hand means handling its API key in the Authorization header against api.routeone.com and building your own polling to track credit application status. Through Jentic you install once, import RouteOne from the API Directory, store the key once, and your agent calls it.
Permission scoping
RouteOne puts the application id in the URL path (/applications/{applicationId}), so a rule can pin your agent to one application: it can read that application's status and nothing else. You choose the operations it may call, so submitting new credit applications is not included unless you add it.
Credential isolation
Your RouteOne 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.
Intent-based discovery
Agents search Jentic by intent such as 'submit a credit application' or 'look up available lenders', and Jentic returns the matching RouteOne 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.
Specific to using RouteOne API through Jentic.
What authentication does the RouteOne API use?
The RouteOne API uses an API key passed in the `Authorization` header. Through Jentic, these credentials are stored encrypted in your Jentic One instance and injected at execution time, so raw secrets never enter the agent context.
Can I submit a credit application with the RouteOne API?
Yes. Use the POST /applications endpoint to submit a buyer's credit application to lenders. The API returns structured JSON responses that agents can parse and act on directly.
How do I check whether a credit application was approved?
Call GET /applications/{applicationId} with the application's ID to retrieve its current status, such as an approved, conditioned, or declined decision from the lender.
What are the rate limits for the RouteOne API?
Rate limits are not specified in the OpenAPI spec. Check the vendor documentation at https://developer.routeone.com/ for current limits. Through Jentic, rate limiting is handled automatically with retry logic built into the execution layer.
How do I submit a credit application through Jentic?
Install the Jentic SDK with pip install jentic, authenticate through Jentic One, the self-hosted execution layer, then search for 'submit credit application'. Jentic returns the matching RouteOne API operation with its input schema. Load the schema and execute the call against POST /applications - credentials are injected automatically.
How many endpoints does the RouteOne API have?
The RouteOne API exposes 4 endpoints covering credit application submission, application status, dealers, and lenders.
Can I limit what my agent is allowed to do with the RouteOne API?
Yes. Because you self-host Jentic One, your own rules decide which RouteOne operations and credentials the agent may use. Since the application id sits in the URL path (/applications/{applicationId}), you can pin the agent to a single application so it only reads that application's status through GET /applications/{applicationId} and nothing else. You choose the operations it may call, so submitting new credit applications via POST /applications is excluded unless you add it, and dealer or lender lookups stay off unless you allow them.
For Agents
Submit automotive credit applications, check their approval status, and look up participating dealers and lenders. Covers 4 operations with apiKey authentication.
Use for: I need to submit a credit application for a car buyer, Check whether a credit application was approved, Get the status of a submitted financing application, List all lenders available for a dealer
Not supported: Does not handle payments, vehicle inventory, or CRM - use for automotive credit application submission and lender lookups only.
Submit automotive credit applications to lenders and track their approval decisions. RouteOne is the finance and lending platform that connects car dealers to indirect-lending networks, so a dealer can send a buyer's credit application to lenders and retrieve the decision without leaving their own system. The API exposes 4 endpoints secured with apiKey authentication, covering credit application submission, status checks, and lender and dealer lookups.
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>