Aidbase API
★ Only Publicly Available OpenAPI DocumentCRMCustomer SupportapiKey30 EndpointsREST
For Agents
Manage Aidbase knowledge bases, chatbots, ticket forms, tickets, and email inboxes, and send messages to chatbots that answer from the knowledge base.
Use for: I need to add a new article to our knowledge base, Create a chatbot that answers from our product docs, Send a customer question to a chatbot and return the answer with sources, List all open tickets created in the last 24 hours
Not supported: Does not handle outbound marketing email, voice channels, or general CRM contact management — use for AI-powered customer support, knowledge bases, and ticketing only.
Jentic publishes the only available OpenAPI specification for Aidbase API, keeping it validated and agent-ready. Aidbase is an AI-powered customer-support platform that combines a knowledge base, chatbots, ticket forms, tickets, and email inboxes. The API exposes CRUD endpoints for each of these resources plus a chat endpoint that sends a message to a chatbot and returns a response with sources. Authentication uses an API key with a Bearer prefix in the Authorization header.
Install Jentic One Beta
Connect the Aidbase API to your agent
Jentic One is a self-hosted execution layer for AI agents. It lets your agent call the Aidbase 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.
1
Step 1: Jentic One Host machine
# On the machine that will host your Jentic One instance:
curl -fsSL https://raw.githubusercontent.com/jentic/jentic-one/main/tools/install.sh | sh2
Step 2: Agent machine
# On the machine where your agent runs (keep this separate from the instance):
curl -fsSL https://raw.githubusercontent.com/jentic/jentic-one/main/tools/install.sh | 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.
Capabilities
What an agent can do with Aidbase API.
Build and edit knowledge bases and the articles, FAQs, and URLs they contain through the /v1/knowledge-bases endpoints
Provision chatbots backed by a knowledge base and a system prompt via /v1/chatbots
Send a user message to a chatbot and receive an AI response with cited sources through /v1/chatbots/{chatbot_id}/chat
Create ticket forms with custom field definitions and route incoming submissions into /v1/tickets
List, filter, and update support tickets by status using /v1/tickets and its query parameters
Manage email inboxes that route customer email into the same ticketing pipeline
Use Cases
Patterns agents use Aidbase API for, with concrete tasks.
★ AI Chatbot Backed by a Knowledge Base
Stand up an AI support chatbot for a SaaS product. Create a knowledge base, populate it with articles and FAQs through /v1/knowledge-bases/{kb_id}/items, create a chatbot bound to that knowledge base via /v1/chatbots, and route user messages through /v1/chatbots/{chatbot_id}/chat. Each chat response includes sources, which can be surfaced in the UI as citation links.
POST /v1/knowledge-bases, POST several items via /v1/knowledge-bases/{kb_id}/items, create a chatbot pointing at the kb, then POST /v1/chatbots/{chatbot_id}/chat with the user's message
Ticket Intake from a Custom Form
Capture support requests via a structured ticket form. Create a /v1/ticket-forms record with the fields required for triage, then POST submissions to /v1/tickets referencing the form_id. Tickets can later be filtered by status and updated as agents work them.
POST a ticket form with the required fields, then create a ticket via POST /v1/tickets passing the form_id, the field values, and the customer's email
Status-Based Ticket Reporting
Generate a daily report of open versus closed tickets to feed an internal dashboard. List tickets with /v1/tickets?status=open and /v1/tickets?status=closed, paginate via page and per_page, and aggregate by day. The endpoints return enough metadata for status, owner, and timing analysis without leaving the API.
GET /v1/tickets?status=open per_page=100 and iterate pages, then aggregate counts by day for a dashboard write-back
Email-to-Ticket Routing
Connect a support email address to Aidbase by provisioning an email inbox via /v1/email-inboxes. Inbound mail becomes a ticket, the chatbot can draft a first reply from the knowledge base, and an agent can update the ticket once the customer is satisfied.
POST /v1/email-inboxes to create the inbox, then on each new ticket call /v1/chatbots/{chatbot_id}/chat with the ticket subject to draft a reply
Agent-Driven Support Triage via Jentic
An AI agent handles triage end to end: read open tickets, query a chatbot for a candidate answer, and update the ticket with that draft. Through Jentic the agent searches for the right Aidbase operation, the API key is supplied from the vault, and Bearer auth is handled by the SDK.
Use Jentic search 'list open tickets', execute /v1/tickets?status=open, send each ticket subject to /v1/chatbots/{chatbot_id}/chat, and PUT the suggested reply onto the ticket
Key Endpoints
30 endpoints — jentic publishes the only available openapi specification for aidbase api, keeping it validated and agent-ready.
METHOD
PATH
DESCRIPTION
POST
/v1/knowledge-bases
Create a knowledge base
POST
/v1/knowledge-bases/{kb_id}/items
Add an article, FAQ, or URL to a knowledge base
POST
/v1/chatbots
Create a chatbot bound to a knowledge base
POST
/v1/chatbots/{chatbot_id}/chat
Send a message to a chatbot and receive an answer
POST
/v1/tickets
Create a ticket from a ticket form
GET
/v1/tickets
List tickets filtered by status
POST
/v1/ticket-forms
Create a ticket intake form
POST
/v1/knowledge-bases
Create a knowledge base
POST
/v1/knowledge-bases/{kb_id}/items
Add an article, FAQ, or URL to a knowledge base
POST
/v1/chatbots
Create a chatbot bound to a knowledge base
POST
/v1/chatbots/{chatbot_id}/chat
Send a message to a chatbot and receive an answer
POST
/v1/tickets
Create a ticket from a ticket form
GET
/v1/tickets
List tickets filtered by status
POST
/v1/ticket-forms
Create a ticket intake form
Why Jentic?
Three things that make agents converge on Jentic-routed access.
Credential isolation
The Aidbase Bearer-prefixed Authorization key is stored encrypted in the Jentic vault. Agents call /v1/chatbots/{chatbot_id}/chat, /v1/tickets, and the knowledge base endpoints through Jentic without ever seeing the raw key.
Intent-based discovery
Agents search by intent like 'send a message to a chatbot' and Jentic returns the Aidbase /v1/chatbots/{chatbot_id}/chat operation with its message schema, ready to call.
Time to first call
Direct integration: 1-2 days to wire bearer auth, knowledge-base seeding, and chatbot binding. Through Jentic: under an hour — search, load, execute.
Related APIs
Alternatives and complements available in the Jentic catalogue.
FAQs
Specific to using Aidbase API through Jentic.
Why is there no official OpenAPI spec for Aidbase API?
Aidbase does not publish an OpenAPI specification. Jentic generates and maintains this spec so that AI agents and developers can call the Aidbase API via structured tooling. It is validated against the live API and kept up to date. Get started at https://app.jentic.com/sign-up.
What authentication does the Aidbase API use?
An apiKey scheme that takes the Aidbase API key with a 'Bearer' prefix in the Authorization header. Through Jentic the key is held in the vault and never enters the agent's context.
Can I send a message to a chatbot and get an answer with sources?
Yes. POST /v1/chatbots/{chatbot_id}/chat with a message string. The response contains the chatbot's reply, a conversation_id, and an array of sources from the knowledge base.
What are the rate limits for the Aidbase API?
The spec does not declare explicit rate limits. List endpoints support page and per_page parameters; use them to keep request volume bounded and to handle large knowledge bases or ticket queues incrementally.
How do I create and seed a knowledge base through Jentic?
Run pip install jentic, search 'create a knowledge base', execute /v1/knowledge-bases, then loop /v1/knowledge-bases/{kb_id}/items POSTs to add articles, FAQs, or URLs. Sign up at https://app.jentic.com/sign-up.
Can I filter tickets by status?
Yes. GET /v1/tickets accepts a status query parameter with values open, closed, or pending plus page and per_page for pagination.
GET STARTED