Install Jentic One Beta
Jentic One is a self-hosted execution layer for AI agents. It lets your agent call the Azure, 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%2Fswaggerhub.sourcecode9%2Fazure" | 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%2Fswaggerhub.sourcecode9%2Fazure" | 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 Azure API.
update
Manage e commerce data programmatically
Integrate Azure into automated workflows
Query and filter Azure records by parameters
Monitor Azure operational status and events
GET STARTED
Patterns agents use Azure API for, with concrete tasks.
★ E-Commerce Operations
Use the Azure to perform e commerce operations programmatically. The API provides 1 endpoints covering core functionality including update.
Call PATCH /qnamaker/v4.0/knowledgebases/{kbId} to update
Data Retrieval and Monitoring
Query Azure resources on a schedule to track changes, generate alerts, or feed downstream dashboards. Agents poll relevant endpoints, compare against previous state, and trigger actions when thresholds are crossed.
Poll the primary Azure endpoint, compare response to last known state, and alert if changed
AI Agent Integration via Jentic
AI agents discover and call Azure 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 apiKey tokens manually.
Search Jentic for 'update', load the operation schema, and execute with Jentic-managed credentials
1 endpoints — api for k2productfeatures.
METHOD
PATH
DESCRIPTION
/qnamaker/v4.0/knowledgebases/{kbId}
update
/qnamaker/v4.0/knowledgebases/{kbId}
update
What agents get from Jentic-routed access to this vendor.
Setup
Wiring this Azure QnA Maker knowledge base API by hand means configuring its Ocp-Apim-Subscription-Key header, targeting the Cognitive Services host, and handling the update call and retries yourself. Through Jentic you install once, import this Azure API from the API Directory, store the subscription key once, and your agent calls it.
Permission scoping
This API puts the knowledge base id in the URL path (/qnamaker/v4.0/knowledgebases/{kbId}), so a rule can pin your agent to one knowledge base and the single update operation it exposes. You choose the operations it may call, so nothing beyond that patch runs unless you add it.
Credential isolation
Your Azure subscription 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 'update a knowledge base', and Jentic returns the matching Azure 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
Alternative e commerce API
Choose Stripe when you need a different approach to e commerce operations
Specific to using Azure API through Jentic.
What authentication does the Azure use?
The Azure uses an API key passed in the `Ocp-Apim-Subscription-Key` 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 update with the Azure?
Yes. Use the PATCH /qnamaker/v4.0/knowledgebases/{kbId} endpoint. The API returns structured JSON responses that agents can parse and act on directly.
What are the rate limits for the Azure?
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 update through Jentic?
Install the Jentic SDK with pip install jentic, authenticate through Jentic One, the self-hosted execution layer, then search for 'update'. Jentic returns the matching Azure operation with its input schema. Load the schema and execute the call - credentials are injected automatically.
How many endpoints does the Azure have?
The Azure exposes 1 endpoints covering qnamaker operations.
Can I limit what my agent is allowed to do with the Azure QnA Maker API?
Yes. Jentic One runs self-hosted on your own infrastructure, so your rules decide which operations and credentials the agent may use. This API exposes only the single PATCH /qnamaker/v4.0/knowledgebases/{kbId} update operation, so you can restrict the agent to that one call and nothing else runs unless you add it. Because the knowledge base id sits in the URL path, you can also pin the agent to one specific knowledge base and keep the encrypted subscription key out of its context.
Know of an official OpenAPI document? Contribute it →
For Agents
Programmatically update. Covers 1 operations with apiKey authentication.
Use for: I need to update, Find available e commerce operations, Get the current status of Azure resources, List all records from Azure
Not supported: Does not handle payments, communications, or crm - use for e-commerce only.
API for k2productfeatures.cognitiveservices.azure.com. The API exposes 1 endpoints secured with apiKey authentication.