Install Jentic One Beta
Jentic One is a self-hosted execution layer for AI agents. It lets your agent call the Qigu Open API Documentation, 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%2Fqigu.app%2Fqigu" | 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%2Fqigu.app%2Fqigu" | 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 Qigu Open API Documentation API.
Returns the list of the countries
Creates a new client
Updates an existing client
Access Qigu Open API Documentation developer tools resources via REST API
Patterns agents use Qigu Open API Documentation API for, with concrete tasks.
GET STARTED
★ Developer Tools Operations
Use the Qigu Open API Documentation to perform developer tools operations programmatically. The API provides 15 endpoints covering core functionality including returns the list of the countries, returns the list of the languages, creates a new client.
Call GET /countries to returns the list of the countries
Automated countries Management
Automate countries operations by combining multiple Qigu Open API Documentation endpoints. Agents can returns the list of the languages and then creates a new client in a single workflow.
Call GET /languages to returns the list of the languages, then verify the result
AI Agent Integration via Jentic
AI agents discover and call Qigu Open API Documentation 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 eliminates the need to read API documentation or handle bearer tokens manually.
Search Jentic for 'returns the list of the countries', load the operation schema, and execute with Jentic-managed credentials
15 endpoints — this document describes the differents endpoints you can use with the **company authentification token** (provided by qigu admin).
METHOD
PATH
DESCRIPTION
/countries
Returns the list of the countries
/languages
Returns the list of the languages
/companies
Creates a new client
/companies
Returns the list of your clients
/companies/{id}
Updates an existing client
/programs
Returns the list of your programs
/journeys
Creates a new journey
/journeys
Returns the list of your distributions
/countries
Returns the list of the countries
/languages
Returns the list of the languages
/companies
Creates a new client
/companies
Returns the list of your clients
/companies/{id}
Updates an existing client
/programs
Returns the list of your programs
/journeys
Creates a new journey
/journeys
Returns the list of your distributions
What agents get from Jentic-routed access to this vendor.
Setup
Wiring the Qigu API by hand means setting up its bearer auth and handling company, program, and journey calls yourself. Through Jentic you install once, import the Qigu API from the API Directory, store the token once, and your agent calls it.
Permission scoping
Qigu puts the company id in the URL path (/companies/{id}), so a rule can pin your agent to one company: it can update that company and nothing else. You choose the operations it may call, so creating journeys is not included unless you add it.
Credential isolation
Your Qigu 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 'list supported countries' or 'create a journey', and Jentic returns the matching Qigu 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 Qigu Open API Documentation API through Jentic.
What authentication does the Qigu Open API Documentation use?
The Qigu Open API Documentation uses a Bearer token 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 returns the list of the countries with the Qigu Open API Documentation?
Yes. Use the GET /countries endpoint. The API returns structured JSON responses that agents can parse and act on directly.
What are the rate limits for the Qigu Open API Documentation?
Rate limits are not specified in the OpenAPI spec. Check the vendor documentation for current limits. Through Jentic, rate limiting is handled automatically with retry logic built into the execution layer.
How do I returns the list of the countries through Jentic?
Install the Jentic SDK with pip install jentic, authenticate through Jentic One, the self-hosted execution layer, then search for 'returns the list of the countries'. Jentic returns the matching Qigu Open API Documentation operation with its input schema. Load the schema and execute the call - credentials are injected automatically.
How many endpoints does the Qigu Open API Documentation have?
The Qigu Open API Documentation exposes 15 endpoints covering countries, companies, files operations.
Can I limit what my agent is allowed to do with the Qigu API?
Yes. Because Jentic One is self-hosted, you write the rules that decide which Qigu operations and credentials your agent may use. Since Qigu puts the company id in the URL path, such as PUT /companies/{id}, you can pin the agent to a single company so it updates that record and nothing else. You also pick the exact operations it may call, so creating journeys with POST /journeys stays off unless you explicitly allow it.
For Agents
Programmatically returns the list of the countries, returns the list of the languages. Covers 15 operations with bearer authentication.
Use for: I need to returns the list of the countries, I want to returns the list of the languages, Search for creates a new client, Find all returns the list of your clients
Not supported: Does not handle payments, communications, or crm - use for developer tools only.
This document describes the differents endpoints you can use with the **Company Authentification Token** (provided by Qigu Admin).<br/>If you provide a **webhook url** in Qigu Admin, our API will call yours when specific events happens. The API exposes 15 endpoints secured with bearer authentication.
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>