Integration Examples

ℹ️

Custom actions require a Builder plan or higher.

Upgrade to Builder →

ℹ️

Body parameters are sent as top-level JSON keys. When you import a cURL whose body has nested objects or arrays, the importer creates dotted keys such as from.email, and those are sent as flat keys, not nested JSON. For an API that needs a nested body, replace those rows with one AI fills it in parameter of type Object or List (see Nested Body Fields).

Slack Notifications

Send messages to Slack channels via webhook.

Configuration

bash

curl -X POST https://hooks.slack.com/services/{{var.SLACK_WEBHOOK_ID}} \
  -H "Content-Type: application/json" \
  -d '{
    "text": "{{message}}",
    "channel": "{{channel}}",
    "username": "Chipp Bot"
  }'

Parameters

Parameter	Source	Configuration
`message`	AI fills it in	Message content to send. Type Text, Required
`channel`	AI fills it in	Target channel. Type Text, Required off
`SLACK_WEBHOOK_ID`	Application variable	Your Slack webhook ID, used in the URL

Usage

“Send a message to #general saying the report is ready”

OpenAI Completions

Call OpenAI’s API for advanced processing.

Configuration

bash

curl -X POST https://api.openai.com/v1/responses \
  -H "Authorization: Bearer {{var.OPENAI_API_KEY}}" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-4.1",
    "input": "{{prompt}}",
    "max_output_tokens": {{maxTokens}}
  }'

Parameters

Parameter	Source	Configuration
`OPENAI_API_KEY`	Application variable (secret)	Your OpenAI API key, used in the header
`input`	AI fills it in	Text for OpenAI to process. Type Text, Required
`max_output_tokens`	AI fills it in	Token limit. Type Whole number, Required off, sample `1000`

Set Type to Whole number on max_output_tokens, so the AI sends a number and not the text "1000".

SendGrid Email

Send transactional emails via SendGrid.

Configuration

bash

curl -X POST https://api.sendgrid.com/v3/mail/send \
  -H "Authorization: Bearer {{var.SENDGRID_API_KEY}}" \
  -H "Content-Type: application/json" \
  -d '{
    "personalizations": [{
      "to": [{"email": "{{recipientEmail}}"}],
      "subject": "{{subject}}"
    }],
    "from": {
      "email": "{{var.FROM_EMAIL}}",
      "name": "{{var.FROM_NAME}}"
    },
    "content": [{
      "type": "text/html",
      "value": "{{emailBody}}"
    }]
  }'

Variables

bash

SENDGRID_API_KEY = SG.abc123...
FROM_EMAIL = noreply@example.com
FROM_NAME = Your Company

Google Sheets

Read and write data to Google Sheets.

Read Data

bash

curl -X GET "https://sheets.googleapis.com/v4/spreadsheets/{{var.SHEET_ID}}/values/{{range}}" \
  -H "Authorization: Bearer {{var.GOOGLE_API_KEY}}"

Append Data

bash

curl -X POST "https://sheets.googleapis.com/v4/spreadsheets/{{var.SHEET_ID}}/values/{{range}}:append" \
  -H "Authorization: Bearer {{var.GOOGLE_API_KEY}}" \
  -H "Content-Type: application/json" \
  -d '{
    "values": [[
      "{{system.timestamp}}",
      "{{system.user_id}}",
      "{{data}}"
    ]]
  }'

Webhook with Dependencies

Multi-step workflow using action dependencies.

Step 1: Create User

bash

curl -X POST https://api.example.com/users \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer {{var.API_KEY}}" \
  -d '{
    "name": "{{userName}}",
    "email": "{{userEmail}}"
  }'

Returns: {"data": {"id": "user_123", "email": "john@example.com"}}

Step 2: Send Welcome Email

Use the user ID from Step 1:

bash

curl -X POST https://api.example.com/emails \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer {{var.API_KEY}}" \
  -d '{
    "user_id": "{{userId}}",
    "template": "welcome",
    "send_at": "{{system.timestamp}}"
  }'

Parameter configuration for user_id:

Source: Output from another action
Action: Create User
JSONPath: $.data.id
Test value: user_123 (sent by Test Request, which has no earlier action output)

Save “Create User” first: the action list only shows saved actions. If the AI calls “Send Welcome Email” before “Create User” has run in the conversation, the call stops and the AI is told to run “Create User” first.

CRM Integration

Update customer records in your CRM.

Configuration

bash

curl -X PATCH https://api.crm.com/v2/contacts/{{contactId}} \
  -H "Authorization: Bearer {{var.CRM_API_KEY}}" \
  -H "Content-Type: application/json" \
  -d '{
    "properties": {
      "last_contact": "{{system.timestamp}}",
      "last_message": "{{summary}}",
      "status": "{{status}}"
    }
  }'

AI Instructions

For summary parameter:

plaintext

Summarize the key points from the conversation in 1-2 sentences

For status parameter:

plaintext

Determine status: 'interested', 'qualified', 'not-interested', or 'follow-up'

Stripe Payment

Create payment intents via Stripe API.

Configuration

bash

curl -X POST https://api.stripe.com/v1/payment_intents \
  -u "{{var.STRIPE_SECRET_KEY}}:" \
  -H "Content-Type: application/x-www-form-urlencoded" \
  -d "amount={{amount}}&currency=usd&customer={{customerId}}"

Parameters

Parameter	Source	Configuration
`STRIPE_SECRET_KEY`	Application variable (secret)	Your Stripe secret key
`amount`	AI fills it in	Amount in cents. Type Whole number
`currency`	Fixed value	`usd`
`customer`	AI fills it in	Stripe customer ID. Type Text

The importer reads a form-encoded -d string as a single data parameter, so add these three body parameters by hand. It also turns -u into a fixed Authorization header that encodes the placeholder text itself, which Chipp cannot resolve. Delete that header and set the Auth tab to Basic Auth with the STRIPE_SECRET_KEY variable as the credential (Stripe uses the key as the username and an empty password). With the Content-Type: application/x-www-form-urlencoded header set, Chipp sends them form-encoded.

Weather API

Fetch weather data for user queries.

Configuration

bash

curl -X GET "https://api.openweathermap.org/data/2.5/weather" \
  -G \
  --data-urlencode "q={{city}}" \
  --data-urlencode "appid={{var.WEATHER_API_KEY}}" \
  --data-urlencode "units=metric"

curl -X POST https://api.github.com/repos/{{var.GITHUB_OWNER}}/{{var.GITHUB_REPO}}/issues \
  -H "Authorization: Bearer {{var.GITHUB_TOKEN}}" \
  -H "Content-Type: application/json" \
  -d '{
    "title": "{{issueTitle}}",
    "body": "{{issueBody}}",
    "labels": {{labels}},
    "assignees": {{assignees}}
  }'

Parameter Configuration

Parameter	Source	Type	AI Instructions
`title`	AI fills it in	Text	Create a concise title for the GitHub issue
`body`	AI fills it in	Text	Write a detailed description of the issue
`labels`	AI fills it in	List	Relevant labels, for example [“bug”, “urgent”]. Required off
`assignees`	AI fills it in	List	GitHub usernames to assign. Required off

Best Practices

1. Error Handling

Always return clear error messages:

json

{
  "success": false,
  "error": "API key invalid. Please check your credentials."
}

2. Rate Limiting

Respect API rate limits:

Add delays between requests
Implement exponential backoff
Cache responses when possible

3. Security

Use HTTPS endpoints only
Store credentials as secret variables
Never log sensitive data
Validate all inputs

4. Performance

Paginate large result sets
Use field selection to minimize data
Implement timeouts (30s max)
Cache frequently accessed data

5. Testing

Test with various inputs
Verify error handling
Check edge cases
Monitor response times

Integration Examples

Slack Notifications

Configuration

Parameters

Usage

OpenAI Completions

Configuration

Parameters

SendGrid Email

Configuration

Variables

Google Sheets

Read Data

Append Data

Webhook with Dependencies

Step 1: Create User

Step 2: Send Welcome Email

CRM Integration

Configuration

AI Instructions

Stripe Payment

Configuration

Parameters

Weather API

Configuration

Usage Examples

GitHub Integration

Configuration

Parameter Configuration

Best Practices

1. Error Handling

2. Rate Limiting

3. Security

4. Performance

5. Testing

Next Steps