Agentic Platform
Documentation API reference Tools Skills

Tools

Knowledge

knowledge MCP Web search

Find answers to how to use Botify.

Answer questions about the Botify application to understand product features, technical concepts, and best practices for using Botify effectively.In any case but the build of a query, if user asks what a specific filter means (for example a dimension, metric, or UI filter) and strictly for the meaning, query the Knowledge tool using the filter name plus the keyword “filters”, then explain the filter to the user using the field description and any relevant documentation you find.

Playground

Your organization, project and token stay in this browser's local storage and are sent straight to the API — this page never sees them.

POST
item
query required The question you want to ask to the Knowledge Agent

Billing

Fixed cost per question asked, plus one knowledge-base lookup. Asked by an AI assistant it uses a knowledge base search; asked directly by a person it returns a written answer instead, which costs several times more.

These usage SKUs can be charged on a call.

SKU Credits Description
Tool call 1 per request Charged once per successful item, on top of any usage below.
Knowledge base answer 4 per query A grounded answer built from an indexed knowledge base, several times the price of a plain search over the same index.
Knowledge base search 15 per 10 query One search over an indexed knowledge base.

Schemas

item is what you send, config how the tool behaves, and the response is what you get back.

Item

object
Properties
query string required

The question you want to ask to the Knowledge Agent

min length 5

Example
{
  "query": "string"
}

Response

object
Properties
search_results array required

List of search results used to generate the answer

Items: DiscoveryEngineSearchResult

answer string required

The answer generated by the Knowledge Agent

Example
{
  "search_results": [
    {
      "document": {
        "body": "string",
        "link": "string",
        "title": "string",
        "sequenced_group_name": "string",
        "dataset_name": "string",
        "description": "string"
      },
      "model_scores": {
        "relevance_score": [
          0.0
        ]
      }
    }
  ],
  "answer": "string"
}

Type Definitions

4 types

These are the available sub-object types that can be used in the properties above.

DiscoveryEngineModelScoresResult object
#
relevance_score array required
DiscoveryEngineStructuredDocumentResult object
#
body string required
link string required
title string required
sequenced_group_name string required
dataset_name string required
description string required
DiscoveryEngineUnstructuredDocumentResult object
#
extractive_answers array required
link string required
title string required

Endpoints

POST http://agents.botify.com/{organization}/{project}/knowledge/process
POST http://agents.botify.com/{organization}/{project}/knowledge/batch_process
POST http://agents.botify.com/{organization}/{project}/knowledge/async_process
POST http://agents.botify.com/{organization}/{project}/knowledge/async_batch_process

See running a long job in the background for the polling flow.

cURL

curl -X POST "http://agents.botify.com/{organization}/{project}/knowledge/process" \
  -H "Authorization: Bearer $BOTIFY_API_TOKEN" \
  -H "Content-Type: application/json" \
  -d '{
  "item": {
    "query": "<query>"
  }
}'

Over MCP

This tool is exposed as the MCP tool knowledge. An MCP client passes organization, project and item as tool arguments. Set up MCP →

Raw metadata