> ## Documentation Index
> Fetch the complete documentation index at: https://docs.base44.com/llms.txt
> Use this file to discover all available pages before exploring further.
# Ask the Google Ads assistant
> This API is in beta. Endpoints, fields, and behavior may still change, so avoid depending on it in production.
Answers a plain-language question about the app's Google Ads campaigns.
The answer is prose written for a person, three to five sentences with no markdown, so read it or show it to someone rather than parsing it. The assistant is a language model with no access to the account's numbers, so it gives general advice shaped by your question rather than findings from your data. Read the reporting endpoints such as [Get Google Ads performance dashboard](/api-reference/get-google-ads-performance-dashboard) for the actual figures.
Pass earlier turns in `history` to ask a follow-up. Only the last ten turns reach the model, and anything before that is dropped with nothing in the response saying so, so keep a long conversation summarized on your side.
An empty `reply` means the model returned nothing, and it comes back under a 200 exactly like a real answer. There is no field that distinguishes the two, so check for an empty string and retry rather than treating it as the assistant having nothing to say.
This endpoint is limited to 20 requests a minute per app, shared with the other Google Ads endpoints that run a language model.
This endpoint accepts a personal API key. Workspace API keys are not authorized for it and are rejected with a 403.
## OpenAPI
````yaml /developers/references/app-management/app-management-openapi.json post /api/apps/{app_id}/google-ads/troubleshoot/ask
openapi: 3.1.0
info:
title: Base44 App Management API
version: 1.0.0
servers:
- url: https://app.base44.com
security:
- ApiKeyAuth: []
paths:
/api/apps/{app_id}/google-ads/troubleshoot/ask:
post:
summary: Ask the Google Ads assistant
description: >-
This API is in beta. Endpoints, fields, and behavior may still
change, so avoid depending on it in production.
Answers a plain-language question about the app's Google Ads campaigns.
The answer is prose written for a person, three to five sentences with
no markdown, so read it or show it to someone rather than parsing it.
The assistant is a language model with no access to the account's
numbers, so it gives general advice shaped by your question rather than
findings from your data. Read the reporting endpoints such as [Get
Google Ads performance
dashboard](/api-reference/get-google-ads-performance-dashboard) for the
actual figures.
Pass earlier turns in `history` to ask a follow-up. Only the last ten
turns reach the model, and anything before that is dropped with nothing
in the response saying so, so keep a long conversation summarized on
your side.
An empty `reply` means the model returned nothing, and it comes
back under a 200 exactly like a real answer. There is no field that
distinguishes the two, so check for an empty string and retry rather
than treating it as the assistant having nothing to say.
This endpoint is limited to 20 requests a minute per app, shared with
the other Google Ads endpoints that run a language model.
This endpoint accepts a personal API key. Workspace API keys are
not authorized for it and are rejected with a 403.
operationId: troubleshoot_ask_api_apps__app_id__google_ads_troubleshoot_ask_post
parameters:
- name: app_id
in: path
required: true
schema:
type: string
description: ID of the app whose Google Ads campaigns to manage.
title: App Id
description: ID of the app whose Google Ads campaigns to manage.
example: 6820f3a4e7b91d003c45a1f2
requestBody:
required: true
content:
application/json:
schema:
title: AskGoogleAdsAssistant
type: object
required:
- question
properties:
question:
type: string
description: >-
What you want to ask about the app's Google Ads campaigns,
in plain language.
example: >-
Why is my Performance Max campaign spending its budget
without converting?
campaign_id:
type: string
description: >-
A campaign ID to mention in the question. It is passed to
the model as text for context only, so the assistant does
not read the campaign's data from it.
example: 68b1c0d4e7b91d003c45a1f2
history:
type: array
description: >-
Earlier turns of the conversation, oldest first. Only the
last ten are used.
items:
type: object
required:
- role
- content
properties:
role:
type: string
description: >-
Who said it. Use `user` for your own turns and
`assistant` for the replies. Any value other than
`user` is treated as the assistant.
example: user
content:
type: string
description: What was said in that turn.
example: Which campaign is spending the most?
example:
- role: user
content: Which campaign is spending the most?
example:
question: >-
Why is my Performance Max campaign spending its budget without
converting?
campaign_id: 68b1c0d4e7b91d003c45a1f2
responses:
'200':
description: The assistant's answer.
content:
application/json:
schema:
$ref: '#/components/schemas/TroubleshootReply'
'401':
description: Missing or invalid credentials.
'403':
description: >-
You don't have access to this app, the app does not exist, or you
used a workspace API key. A missing app and an app you cannot reach
are deliberately the same answer.
'422':
description: Validation Error
content:
application/json:
schema:
$ref: '#/components/schemas/HTTPValidationError'
'429':
description: >-
The app has used up its 20 language-model requests a minute. Retry
later.
components:
schemas:
TroubleshootReply:
properties:
reply:
type: string
title: Reply
description: >-
The answer, as three to five sentences of plain prose with no
markdown and no code blocks. It is written for a person to read, so
do not parse it. An empty string means the model returned nothing,
which you cannot tell apart from a genuinely empty answer, so treat
it as a failed call and retry.
example: >-
Your campaign is spending its full daily budget but converting below
the account average, which usually points at the landing page rather
than the targeting. Check that the page loads quickly on mobile and
that the offer matches the ad copy. Narrowing the geo targets to
your best-performing region would also concentrate the budget.
type: object
required:
- reply
title: TroubleshootReply
description: The assistant's answer.
HTTPValidationError:
properties:
detail:
items:
$ref: '#/components/schemas/ValidationError'
type: array
title: Detail
type: object
title: HTTPValidationError
ValidationError:
properties:
loc:
items:
anyOf:
- type: string
- type: integer
type: array
title: Location
msg:
type: string
title: Message
type:
type: string
title: Error Type
type: object
required:
- loc
- msg
- type
title: ValidationError
securitySchemes:
ApiKeyAuth:
type: apiKey
in: header
name: api_key
description: Personal API key.
````