Skip to main content

Documentation Index

Fetch the complete documentation index at: https://mintlify.com/arainey2022/myaskai-docs/llms.txt

Use this file to discover all available pages before exploring further.

The Query API is the simplest way to integrate My AskAI into your own product or workflow. Send a single question, receive a single answer — along with the knowledge-base sources that were used to generate it and a confidence indicator. It is stateless: each call is independent and no conversation history is maintained between requests. If you need multi-turn conversations, see the Chat API.
The question field is capped at 750 characters. Requests that exceed this limit return a 400 error with the message: "This question is too long. Please ensure questions are less than 750 characters."

​
Endpoint

POST https://api.myaskai.com/v1/query
Authentication: Bearer token in the Authorization header. See Introduction → Authentication.

​
Request Parameters

​
question
string
required
The question you want to ask your AI agent. Maximum 750 characters.
​
agent_id
string
required
The unique identifier of the My AskAI agent to query. Find this in your dashboard under Settings → API.
​
user_id
string
An optional identifier for the end user asking the question. Used for analytics and, when combined with the User Data API, enables personalised responses.
​
context
object
An optional free-form object containing additional context to pass to the agent. For example, you might include the page the user is currently viewing or their account tier.
{
  "page": "billing",
  "plan": "pro"
}

​
Example Request

curl -X POST https://api.myaskai.com/v1/query \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "question": "How do I download my invoice?",
    "agent_id": "agt_abc123",
    "user_id": "usr_987",
    "context": {
      "page": "billing"
    }
  }'

​
Response Fields

​
answer
string
The AI-generated answer to the question, grounded in the content from your agent’s knowledge base.
​
sources
array
An array of knowledge-base sources the agent referenced when generating the answer. Each item contains:
​
sources[].title
string
The title of the source document or page.
​
sources[].url
string
The URL of the source, if available.
​
confidence
string
A qualitative indication of the agent’s confidence in the answer. One of high, medium, or low.
​
unknown_answer
string
Present and set to "yes" when the agent was unable to find a relevant answer in its knowledge base. When this field appears, the answer field will contain the agent’s “I don’t know” response.
​
human_handover
boolean
Present and set to true when a Guidance rule triggered a human-handover recommendation for this question.

​
Example Response

{
  "answer": "To download your invoice, go to Account Settings → Billing, then click 'Manage subscription on Stripe'. In Stripe, navigate to Invoice history and click the arrow next to the relevant invoice to download it.",
  "sources": [
    {
      "title": "Download an invoice",
      "url": "https://help.myaskai.com/account-management/billing/download-an-invoice"
    }
  ],
  "confidence": "high"
}

​
Example: Answer Not Found

{
  "answer": "I'm sorry, I don't have enough information to answer that question. You can speak to a member of our team if you'd like.",
  "sources": [],
  "confidence": "low",
  "unknown_answer": "yes"
}

​
Error Codes

HTTP statusDescription
400 Bad RequestThe question or agent_id field is missing, or question exceeds 750 characters.
401 UnauthorizedThe Authorization header is missing or the API key is invalid.
429 Too Many RequestsYou have exceeded the rate limit for this API key. Back off and retry.
500 Internal Server ErrorAn unexpected error occurred on our servers. Retry with exponential back-off.
When building internal tools or Zapier workflows, the Query API is all you need. For a fully conversational interface where follow-up questions reference earlier answers, use the Chat API instead.

Build docs developers (and LLMs) love

Get started for freeTalk to us