Install Jentic One Beta
Jentic One is a self-hosted execution layer for AI agents. It lets your agent call the Fleximize Applications 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%2Ffleximize.com%2Ffleximize" | 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%2Ffleximize.com%2Ffleximize" | 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 Fleximize Applications API.
Submit business loan applications with applicant and company details
Check the current status of a submitted application by its id
Link a customer's open banking data to an application for underwriting
Upload supporting documents against an application
Retrieve the allowed document types before uploading
GET STARTED
Patterns agents use Fleximize Applications API for, with concrete tasks.
★ Agent-Driven Loan Submission
An AI agent connected through Jentic can submit a business loan application to Fleximize without a developer wiring the token exchange and the is_test onboarding flag. The agent submits the application, reads back its status by id, and uploads the documents the lender needs. Jentic injects the bearer token at call time so the credential never reaches the agent.
Submit a business loan application, read its status by application id, then upload the requested documents
Open Banking Underwriting
Lenders assessing an applicant can attach the applicant's open banking data to the application rather than waiting for manual statements. The agent links the open banking data to an existing application so Fleximize can run its checks. This shortens the path from application to underwriting decision.
Link a customer's open banking data to an existing application and confirm the application status updated
Document Collection
An application often needs supporting paperwork before a decision. The agent first retrieves the allowed document types, then uploads each required document against the application id. This keeps uploads valid and the application complete.
Fetch the allowed document types, then upload a bank statement and an ID document against the application
6 endpoints — the fleximize applications api submits and tracks business loan applications to the fleximize sme lender.
METHOD
PATH
DESCRIPTION
/application
Submit a loan application
/application/{application_id}
Get an application's current status
/application/{application_id}
Link customer open banking data
/application/{application_id}/upload
Upload a supporting document
/application/document-types
List allowed document types
/application
Submit a loan application
/application/{application_id}
Get an application's current status
/application/{application_id}
Link customer open banking data
/application/{application_id}/upload
Upload a supporting document
/application/document-types
List allowed document types
What agents get from Jentic-routed access to this vendor.
Setup
Wiring Fleximize by hand means posting your credentials to the token endpoint for a JWT bearer token, sending it on each call, and remembering the is_test flag so onboarding leads do not trigger credit checks. Through Jentic you install once, import Fleximize from the API Directory, store the credential once, and your agent calls it.
Permission scoping
Fleximize puts the application id in the URL path, for example /application/{application_id}, so a rule can pin your agent to one application: it can read status and upload documents for that application and nothing else. You choose which operations it may call, so submitting new applications is not included unless you add it.
Credential isolation
Your Fleximize bearer token 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 loan application' or 'link open banking data', and Jentic returns the matching Fleximize 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 Fleximize Applications API through Jentic.
What authentication does the Fleximize Applications API use?
Per its OpenAPI spec, the Fleximize Applications API uses a JWT bearer token obtained from the token endpoint, which is itself public. Through Jentic the token is stored encrypted by your own instance and injected at call time, so it never reaches the agent.
Is there a Fleximize MCP server?
You don't need an MCP server to give your agent Fleximize. Jentic connects it directly from the API Directory: import it, store your credential once, and your agent calls operations like submitting an application or uploading a document on demand, without loading another server's tool definitions into its context.
Can I limit what my agent is allowed to do with Fleximize?
Yes. Fleximize puts the application id in the URL path, so a rule can pin your agent to one application and allow only status reads and document uploads, so it cannot submit a brand-new application unless you add that operation, and every call it makes is logged. This matches a bot that chases paperwork on an existing application without opening new ones.
Can I check an application's status with the Fleximize Applications API?
Yes. Call the status operation with the application id returned when you submitted it, and the API returns the application's current status. You can poll it as the application moves through review.
What are the rate limits for the Fleximize Applications API?
The API documentation states that calls are rate-limited to 60 calls per minute. Keep bulk submissions within that ceiling, and use the is_test flag during onboarding so test applications do not trigger credit checks.
How do I submit a loan application with the Fleximize Applications API through Jentic?
Search Jentic for 'submit a loan application', which returns the application submission and status operations with their input schemas. The agent submits the application, reads its status by id, and uploads the required documents, with your stored token injected at call time. To run it on your own infrastructure, install Jentic One from its GitHub repo.
Know of an official OpenAPI document? Contribute it →
For Agents
Submit business loan applications, track their status, link open banking data, and upload supporting documents to the Fleximize SME lender. Authenticated with a JWT bearer token.
Use for: I need to submit a loan application for a business, Check the status of a submitted application, Link open banking data to an application, Upload a bank statement to an application
Not supported: Does not handle loan servicing, repayments, or disbursement. Use for Fleximize business loan application submission and tracking only.
The Fleximize Applications API submits and tracks business loan applications to the Fleximize SME lender. It creates an application, returns its current status by application id, and accepts supporting documents once the allowed document types are retrieved. It can link a customer's open banking data to an application to support underwriting. Calls use a JWT bearer token obtained from the token endpoint, and an is_test flag lets partners onboard without triggering credit checks.
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>