Chatbots - AI Puffer

Overview

Use Chatbots to add AI chatbots to WordPress. Each chatbot has its own model, instructions, knowledge sources, capabilities, display settings, popup settings, limits, connected apps, and rules. If the Chatbots menu is not visible, enable Chatbots under AI Puffer > Settings > Modules and confirm that your WordPress role has access to it.

Live chatbot demo

Open the frontend chatbot example.

Deploy

Use popup, on-page, or external embed.

Model

Choose the provider, model, instructions, and memory.

Knowledge

Use vectors, page context, and knowledge sources.

Capabilities

Enable file upload, web search, images, and voice.

Display

Customize colors, popup, suggested questions, consent, and labels.

Limits

Set usage limits and credit behavior.

Connected Apps

Send chatbot events to Slack, HubSpot, Notion, and more.

Rules

Trigger actions from chatbot events and conditions.

Create a Chatbot

Go to AI Puffer > Chatbots.
Click the + button next to the chatbot selector.

A new bot is created immediately with the default name New Chatbot.
Select the chatbot from the dropdown.
Open Chatbot settings > Display > Chat text to rename it.

Use the live preview to test the chatbot before publishing it.

Use the chatbot actions menu for saved chatbots:

Action	What it does
Duplicate	Creates a copy of the current chatbot.
Reset	Resets the current chatbot settings.
Delete	Deletes the chatbot. The default chatbot cannot be deleted.

Deploy a Chatbot

Each chatbot has a . For example:

[aipkit_chatbot id=123]

On-page Chatbot

Select the chatbot.
Turn Popup off in the preview bar.
Copy the shortcode from the preview bar, or open Chatbot settings > Publish > WordPress shortcode.

Paste it into a page, post, block, or shortcode area.
Publish or update the page.

Select the chatbot.
Turn Popup on in the preview bar.
Turn Site-wide on if the launcher should appear across the site.

Configure the popup design on the main screen, or open Chatbot settings > Display for more popup options.
Save and test the site frontend.

Site-wide popup mode is global. Enabling it for one chatbot turns it off for the previous site-wide popup chatbot.

External Embed

External Embed lets you place a chatbot on a non-WordPress site while managing it from WordPress.

Select the chatbot.
Open Chatbot settings.
Open Publish > External embed.

Copy the embed code.
Add allowed websites, one URL per line.
Paste the embed code into the external site.

Set allowed domains before using external embed on a production site. Do not leave external embeds open to domains you do not control.

Model and Instructions

Use the main chatbot builder to choose the chatbot model and write instructions. Open Chatbot settings > AI behavior > Model for response tuning.

Setting	Use it for
Model	Model used by this chatbot.
Instructions	System instructions for the chatbot. Use `[date]` when the bot needs today’s date in its instructions.
Chatbot name	Internal chatbot name shown in the Chatbots screen. Open Chatbot settings > Display > Chat text to edit it.
Temperature	Response variation. Lower values are more predictable.
Context	Maximum completion tokens for the model response.
Messages	Number of previous conversation messages included as history.
Session memory	Only applies when the chatbot uses OpenAI. AI Puffer stores the OpenAI response ID and sends it with the next message so OpenAI can continue the same conversation state.
Reasoning	Reasoning effort for supported models. Keep it set to None for faster responses; higher values can make replies slower.

Session memory applies only to OpenAI chatbots. When enabled, conversation continuity depends on OpenAI response IDs, so review this setting before using it for privacy-sensitive chatbots.

Knowledge

Knowledge controls the information a chatbot can use before it answers. It can read the current page content, search trained vector data, or use both depending on the chatbot setup. Use the main Knowledge card to add website content, text, Q&A, or files for the selected chatbot. Open Chatbot settings > Conversation > Knowledge when you need to choose the retrieval source, vector storage, stores or collections, embedding model, Results, or Minimum match.

Vector

Vector is the better option when you want to train the chatbot with your own content. AI Puffer converts your content into searchable chunks. When a visitor asks a question, the chatbot retrieves the closest matching chunks and uses them as context for the answer.

OpenAI

OpenAI Vector Stores are the simplest option when the chatbot uses OpenAI. To create a store:

Go to AI Puffer > Knowledge Base > Stores.
Select OpenAI as the provider.
Click Create Store.

Enter a store name and create it.
Go to AI Puffer > Knowledge Base > Data and add data to the store.

To use it in a chatbot:

Go to AI Puffer > Chatbots and select the chatbot.
Open Chatbot settings > Conversation > Knowledge.
Turn on Use vector search.
Open the vector search settings.
Set Knowledge storage to OpenAI.

Select one or two vector stores.
Save the chatbot.

Pinecone

Pinecone stores vectors in an index. AI Puffer creates those vectors with the embedding model you choose. The Pinecone index dimension must match the embedding model. For example, if your index is 3072 dimensions, use a 3072-dimension embedding model. Use the same embedding model when adding data and when enabling Pinecone in the chatbot.

If the Pinecone index dimension does not match the embedding model, search can fail or return poor context.

To create an index:

Add your Pinecone credentials in AI Puffer > Settings > Integrations.

Go to AI Puffer > Knowledge Base > Stores.
Select Pinecone as the provider.
Select the embedding model you want to use.
Click Create Store.

Enter an index name and use the dimension for the selected embedding model.
Create the index, then add data with the same embedding model.

To use it in a chatbot:

Go to AI Puffer > Chatbots and select the chatbot.
Open Chatbot settings > Conversation > Knowledge.
Turn on Use vector search.
Open the vector search settings.
Set Knowledge storage to Pinecone.
Select the Pinecone index.
Select the same embedding provider and model used when you added the data.
Save the chatbot.

Qdrant

Qdrant stores vectors in collections. AI Puffer creates those vectors with the embedding model you choose. The Qdrant collection size must match the embedding model. For example, if your collection is 3072 dimensions, use a 3072-dimension embedding model. Use the same embedding model when adding data and when enabling Qdrant in the chatbot.

If the Qdrant collection size does not match the embedding model, search can fail or return poor context.

To create a collection:

Add your Qdrant URL and API key in AI Puffer > Settings > Integrations.

Go to AI Puffer > Knowledge Base > Stores.
Select Qdrant as the provider.
Select the embedding model you want to use.
Click Create Store.

Enter a collection name and use the dimension for the selected embedding model.
Create the collection, then add data with the same embedding model.

To use it in a chatbot:

Go to AI Puffer > Chatbots and select the chatbot.
Open Chatbot settings > Conversation > Knowledge.
Turn on Use vector search.
Open the vector search settings.
Set Knowledge storage to Qdrant.
Select one or more collections.
Select the same embedding provider and model used when you added the data.
Save the chatbot.

Chroma

Chroma stores vectors in collections. AI Puffer creates those vectors with the embedding model you choose. Chroma collections do not require a dimension when they are created in AI Puffer, but stored vectors still need a consistent dimension. Use the same embedding model when adding data and when enabling Chroma in the chatbot.

If the Chroma collection contains vectors from a different embedding model, search can fail or return poor context.

To create a collection:

Add your Chroma endpoint, tenant, database, and API key in AI Puffer > Settings > Integrations.

Go to AI Puffer > Knowledge Base > Stores.
Select Chroma as the provider.
Click Create Store.

Enter a collection name.
Create the collection, then add data with the same embedding model.

To use it in a chatbot:

Go to AI Puffer > Chatbots and select the chatbot.
Open Chatbot settings > Conversation > Knowledge.
Turn on Use vector search.
Open the vector search settings.
Set Knowledge storage to Chroma.
Select one or more collections.
Select the same embedding provider and model used when you added the data.
Save the chatbot.

Results and Minimum Match

For OpenAI, Pinecone, Qdrant, and Chroma, use these settings to control how much vector context is added to the answer.

Setting	How it works	Example
Results	How many pieces of your content the chatbot is allowed to use for one answer.	`3` means the chatbot can use up to 3 matching pieces from your content.
Minimum match	How closely a piece of content must match the visitor’s question before the chatbot can use it.	Lower values allow looser matches. Higher values allow only stronger matches.

If answers miss useful context, increase Results or lower Minimum match. If answers include unrelated context, lower Results or raise Minimum match. After testing, open Usage > Logs and check the Score badge in the conversation details.

Start with a small result count and a moderate minimum match. Then use the Score badge in logs to tune the chatbot with real questions.

Scores show which vector results matched the visitor question and help you tune the minimum match.

Embedding Models

Pinecone, Qdrant, and Chroma need an because AI Puffer must turn your content and the visitor question into vectors before it can search. OpenAI Vector Stores do not need this setting in AI Puffer. OpenAI handles the vector store search on its side.

For Pinecone, Qdrant, and Chroma, use the same embedding model when adding data and when enabling the chatbot knowledge storage.

OpenAI

Model	Dimension
`text-embedding-3-small`	1536
`text-embedding-3-large`	3072
`text-embedding-ada-002`	1536

Google

Model	Dimension
`gemini-embedding-2-preview`	3072
`gemini-embedding-001`	3072
`models/text-embedding-004`	768

OpenRouter

Model	Dimension
`baai/bge-base-en-v1.5`	768
`baai/bge-large-en-v1.5`	1024
`baai/bge-m3`	1024
`google/gemini-embedding-001`	3072
`google/gemini-embedding-2-preview`	3072 by default. Supports 128-3072.
`intfloat/e5-base-v2`	768
`intfloat/e5-large-v2`	1024
`intfloat/multilingual-e5-large`	1024
`mistralai/mistral-embed-2312`	1024
`nvidia/llama-nemotron-embed-vl-1b-v2:free`	2048
`openai/text-embedding-3-large`	3072
`openai/text-embedding-3-small`	1536
`openai/text-embedding-ada-002`	1536
`perplexity/pplx-embed-v1-0.6b`	1024
`perplexity/pplx-embed-v1-4b`	2560
`qwen/qwen3-embedding-4b`	2560
`qwen/qwen3-embedding-8b`	4096
`sentence-transformers/all-minilm-l12-v2`	384
`sentence-transformers/all-minilm-l6-v2`	384
`sentence-transformers/all-mpnet-base-v2`	768
`sentence-transformers/multi-qa-mpnet-base-dot-v1`	768
`sentence-transformers/paraphrase-minilm-l6-v2`	384
`thenlper/gte-base`	768
`thenlper/gte-large`	1024

Ollama

Model	Dimension
`nomic-embed-text-v2-moe`	768
`qwen3-embedding` / `qwen3-embedding:8b`	4096
`qwen3-embedding:4b`	2560
`qwen3-embedding:0.6b`	1024
`embeddinggemma`	768
`nomic-embed-text`	768
`mxbai-embed-large`	1024
`bge-m3`	1024
`snowflake-arctic-embed` / `snowflake-arctic-embed:l`	1024
`snowflake-arctic-embed:m`	768
`snowflake-arctic-embed:m-long`	768
`snowflake-arctic-embed:s`	384
`snowflake-arctic-embed:xs`	384
`all-minilm` / `all-minilm:l6`	384
`all-minilm:l12`	384
`paraphrase-multilingual`	768
`snowflake-arctic-embed2`	1024
`granite-embedding:30m`	384
`granite-embedding` / `granite-embedding:278m`	768
`bge-large`	1024

Azure

Azure OpenAI embedding deployments are synced from your Azure resource. Use the dimension of the model behind the deployment.

Add Knowledge

Use the Knowledge card on the chatbot screen to choose what the selected chatbot should know. The card has two source choices:

Source	Use it for	How it works
My website	Add published WordPress content.	Pages and Posts are selected by default. Click Add knowledge to add those pages and posts to the chatbot.
Other sources	Add text, Q&A, or files.	Click the + button to open the source panel, then choose the content type you want to add.

To add website content:

Go to AI Puffer > Chatbots and select the chatbot.
Find the Knowledge card.
Leave My website selected.
Click Add knowledge to add the default Pages and Posts.
To change which WordPress content types are included, click the + button on My website.
Select or unselect content types such as pages, posts, products, or other public post types available on your site.
Click Add knowledge.

After website knowledge exists, the status changes to Knowledge ready and the button changes to Update knowledge. Click Update knowledge when you want to refresh the chatbot with the latest selected website content. To add other sources:

Click the + button on Other sources.
Choose Text, Q&A, or Files from Content type.
For Text, paste the content the chatbot should know.
For Q&A, enter a Title / Question and Answer. You can also add from common questions.
For Files, click Choose files and upload .pdf, .docx, .txt, .md, .csv, or .json files.
Click Add knowledge. For files, click Upload after choosing files.

The knowledge status shows No knowledge yet, Adding knowledge…, Knowledge ready, or Failed. Click the ? on the status pill to see knowledge details, including entries, queued items, processing items, failed items, View knowledge, and Stop training when a website update is running. Use Knowledge entries on the chatbot screen, or AI Puffer > Knowledge Base > Data, to review and manage existing sources.

Page Context

Adds the current page or post content to the chatbot context. When this feature is enabled, the chatbot will use the current page’s content as part of its contextual understanding. If the page has an excerpt, that excerpt will be used directly as the bot’s context.

If no excerpt is available, the plugin will automatically generate a short summary of the page content and feed that to the bot instead. This is ideal for creating page-specific chatbots.

Capabilities

Capabilities are optional features the chatbot can use during a conversation. They let visitors upload files, search the web, attach images, generate images, or use voice features when those options are enabled. Enable only the capabilities you want your chatbot to offer.

File Upload

File upload lets visitors attach a document to the current chat. AI Puffer reads the file, prepares it for the selected vector provider, and uses the matching file content as context for the visitor’s next messages. File upload uses the chatbot’s Knowledge storage setting: OpenAI, Pinecone, Qdrant, Chroma, or Anthropic Files when the chatbot provider is Anthropic. Visitors can upload .txt and .pdf files. The frontend limit is 20 MB, but your WordPress or server upload limit can be lower.

Text-based PDFs work best. Scanned PDFs may not provide usable text unless they contain OCR text.

To enable file upload:

Go to AI Puffer > Chatbots and select the chatbot.
Open Chatbot settings > Conversation > Knowledge.
Turn on Use vector search.
Configure the Knowledge storage settings.

Open Chatbot settings > Conversation > Capabilities.
Turn on File upload.
Save the chatbot.

Test the chatbot on the frontend and upload a .txt or .pdf file.

Web Search

Web Search lets a chatbot use online sources while answering. When enabled, the chatbot input shows a web/search toggle on the frontend. If the frontend toggle is off, the chatbot answers without web search even when the capability is enabled in the admin. Web Search is available for OpenAI, Google, Anthropic, OpenRouter, and xAI models that support web search.

Web search has two controls: the admin capability setting enables the feature, and the frontend toggle decides whether a specific visitor message uses it.

To enable web search:

Go to AI Puffer > Chatbots and select the chatbot.
Choose an OpenAI, Google, Anthropic, OpenRouter, or xAI model.
Open Chatbot settings > Conversation > Capabilities.
Turn on Web search.
Open the web search settings.

Configure the provider settings.
Save the chatbot.
Test the chatbot on the frontend.

These options appear for every web search provider:

Option	What it does
Web toggle default on	Starts the frontend web/search toggle enabled.
Show sources	Shows source links under replies when the provider returns them.
Sources label	Changes the label shown above source links.
Searching web text	Changes the temporary status text shown while a web search is running.

Provider-specific options are shown based on the chatbot engine. xAI uses the shared web search options above and does not add provider-specific web settings.

OpenAI
Google
Anthropic
OpenRouter

Option	What it does
Search context size	Controls how much web-search context OpenAI can use.
User location	Sends approximate location only when local results matter.

Option	What it does
Mode	Controls Gemini grounding mode.
Retrieval threshold	Applies only to Dynamic mode. Lower values search more often.

Option	What it does
Max uses	Limits web searches per answer.
User location	Sends approximate country, city, region, or timezone.
Allowed domains	Restricts web search to specific domains.
Blocked domains	Excludes specific domains.
Cache TTL	Sets optional Anthropic cache time: None, 5 minutes, or 1 hour.

Option	What it does
Engine	Chooses Auto, Native, or Exa search when supported.
Max results	Limits search results from 1 to 10.
Search prompt	Adds search-specific instructions.

Images and Vision

Image capabilities cover two separate features:

Image analysis sends an uploaded image to the chatbot model so it can answer questions about the image.
Image generation creates a new image when the visitor types a configured image command.

Image Analysis

Image analysis lets visitors attach an image to a chat message. The image is sent with the next message to the chatbot’s selected model. Image analysis uses the chatbot’s selected provider and model.

Image analysis is model-dependent. If the option is missing or replies fail, choose a vision-capable model and sync models again.

Provider	Support	Notes
OpenAI	Yes	Uses the selected OpenAI chat model.
Anthropic	Yes	Uses the selected Claude chat model.
xAI	Yes	Uses a selected Grok model that supports image input.
OpenRouter	Model-dependent	The selected model must support image input. Sync models if the option does not appear.
Ollama	Model-dependent	The selected local model must be vision-capable. Sync Ollama models first.
Google	No	Chatbot image analysis is not exposed for Google.
Azure	No	Chatbot image analysis is not exposed for Azure.
DeepSeek	No	Chatbot image analysis is not exposed for DeepSeek.

Visitors can upload one image per message, with a 20 MB frontend limit. xAI image analysis accepts JPG/JPEG and PNG files. Other supported providers can also accept WEBP when their model supports it. To enable image analysis:

Go to AI Puffer > Chatbots and select the chatbot.
Select a supported provider and model.
Open Chatbot settings > Conversation > Capabilities.
Turn on Image analysis.

Save the chatbot.
Test the chatbot on the frontend.

On the frontend, visitors use the image upload button, select an image, type a question, and send the message. If File Upload and Image Analysis are both enabled, the attachment button opens a small menu.

Image Generation

Image generation lets visitors create a new image from a chat command. The visitor types a trigger followed by a prompt, for example:

/image a clean product photo on a white background

Each command returns one image. Image generation uses a separate image model. It does not use the chatbot’s answer model.

Image generation uses the image model selected in Capabilities, not the chatbot answer model.

Provider	Support	Model source
OpenAI	Yes	Built-in GPT Image models.
Google	Yes	Synced Google image models.
Azure	Yes	Synced Azure image deployments.
OpenRouter	Model-dependent	Synced OpenRouter models with image output.
xAI	Yes	Synced xAI image models such as `grok-imagine-image`.
Replicate	Yes	Add the API key under Settings > Integrations > Replicate, then sync models.

The chatbot image generation model list includes those image providers only. If a model is missing, configure the provider and sync models in AI Providers. To enable image generation:

Go to AI Puffer > Chatbots and select the chatbot.
Open Chatbot settings > Conversation > Capabilities.
Turn on Image generation.
Open the image generation settings.
Select the image model.
Set the image triggers.
Save the chatbot.
Test the command on the frontend.

Triggers are comma-separated and must start with /. Examples:

/image, /generate, /draw

When a visitor uses an image trigger, AI Puffer extracts the prompt after the trigger and sends it to the selected image model. The original command is saved in the conversation log, and the generated image reply is shown in the chat.

Audio and Speech

Audio and speech capabilities are configured per chatbot under Chatbot settings > Conversation > Capabilities.

Capability	What it does
Speech to Text	Records visitor speech, transcribes it, and sends the text as the chat message.
Text to Speech	Adds a play button to assistant replies. Auto play can read replies automatically.
Realtime Voice	Starts a live voice session with OpenAI Realtime.

Speech to Text

Speech to Text adds a microphone button to the chatbot input. When a visitor clicks the microphone, AI Puffer records the audio in the browser, uploads it to WordPress, sends it to the speech-to-text provider, then submits the transcript as the user message. Speech to Text is currently available for OpenAI.

Provider	Speech to Text model
OpenAI	`whisper-1`

To enable speech to text:

Configure OpenAI in AI Providers.
Go to AI Puffer > Chatbots and select the chatbot.
Open Chatbot settings > Conversation > Capabilities.
Turn on Speech to text.

Select the model if the model selector is shown.
Save the chatbot and test the microphone on the frontend.

Speech to Text needs browser microphone permission and HTTPS. Localhost can be used for testing without HTTPS. Recorded audio uploads are limited to 4 MB by default.

Text to Speech

Text to Speech adds playback controls for assistant replies. When a visitor clicks the play button, AI Puffer sends the assistant reply text to the selected text-to-speech provider and plays the returned audio in the browser. Text to Speech is available for Google, OpenAI, and ElevenLabs.

Provider	Text to Speech models
OpenAI	`tts-1`, `tts-1-hd`
ElevenLabs	`eleven_v3`, `eleven_multilingual_v2`, `eleven_flash_v2_5`, `eleven_flash_v2`
Google	Uses synced Google voices.

To enable text to speech:

Go to AI Puffer > Chatbots and select the chatbot.
Open Chatbot settings > Conversation > Capabilities.
Turn on Text to speech.
Open the text-to-speech settings.
Select the provider.
Select the voice and model fields shown for that provider.
Enable Auto play only if replies should play automatically.
Save the chatbot and test the play button on an assistant reply.

ElevenLabs voices and models appear only after the ElevenLabs API key is saved under Settings > Integrations.

Realtime Voice Agents

Realtime Voice is separate from Speech to Text and Text to Speech. It creates a live session with OpenAI Realtime, streams microphone audio, receives spoken replies, and logs completed turns. Realtime Voice is currently available for OpenAI.

Provider	Realtime models
OpenAI	`gpt-4o-realtime-preview`, `gpt-4o-mini-realtime`

To enable realtime voice:

Configure OpenAI in AI Providers.
Go to AI Puffer > Chatbots and select the chatbot.
Open Chatbot settings > Conversation > Capabilities.
Turn on Realtime voice.
Open the realtime voice settings.
Select the realtime model.
Select the voice.
Choose turn detection.
Save the chatbot and test voice mode on the frontend.

Realtime options:

Setting	What it does
Model	OpenAI Realtime model used for the voice session.
Voice	Voice used for spoken replies.
Direct voice mode	Popup-only. The popup launcher starts and stops the voice session directly, and the in-chat realtime button is hidden.
Noise reduction	Applies input audio noise reduction before the model receives the microphone stream.
Audio format	Sets the input and output audio format. Available values are `pcm16`, `g711_ulaw`, and `g711_alaw`.
Response speed	Controls spoken reply speed from `0.25` to `1.5`.

Turn detection options:

Mode	Behavior
None	No server voice activity detection. Use this for push-to-talk style sessions.
Automatic	Uses server voice activity detection. This is the default.
Smart	Uses semantic voice activity detection, so the model can wait for a more complete thought before replying.

Realtime sessions create chat log entries for the user transcript and assistant transcript when a turn completes. If OpenAI returns usage data, AI Puffer records the token usage against the chatbot.

Realtime Voice uses microphone access and an OpenAI Realtime model. Test it on HTTPS and review costs in your OpenAI account.

Display

Use the main chatbot screen for quick visual changes such as chat photo, welcome message, widget colors, and launcher icon. Open Chatbot settings > Display for chat text, launcher behavior, welcome-message timing, and publish options.

Choose a color preset from Widget colors on the main chatbot screen. To build your own theme, choose the custom option and open the custom editor. The editor lets you change the main colors, bubble radius, font, inline width, popup width, chat height, and advanced colors for messages, header, footer, input area, buttons, and sidebar. Use Reset to return the custom theme fields to their defaults.

Popup mode adds a launcher button to the page. When the visitor clicks it, the chatbot opens in a floating chat window. To configure a popup:

Go to AI Puffer > Chatbots and select the chatbot.
Turn on Popup in the preview bar.
Turn on Site-wide if the launcher should appear across the site.
Use the main screen to set the chat photo, welcome message, widget colors, and launcher icon.
Open Chatbot settings > Display.
Configure Launcher and Welcome message options.
Save the chatbot and test it on the frontend.

Setting	Use it for
Position	Place the launcher in a page corner. Options are bottom right, bottom left, top right, and top left.
Icon style	Set the launcher icon style to circle, square, or original.
Size	Set the launcher size to small, medium, large, or x-large.
Auto-open	Open the popup automatically after a delay, or keep it off.
Welcome message	Show a short message near the launcher. Set the text on the main screen and timing, size, frequency, desktop/mobile visibility, and dismiss behavior in Chatbot settings > Display > Welcome message.
Online text	Set the status text shown in the chatbot header.
Launcher icon	Choose a built-in launcher icon or upload a custom icon.
Chat photo	Choose a built-in header avatar or upload a custom image.

Chat Options

Open Chatbot settings > Conversation > Chat options to choose which controls appear in the chatbot.

Setting	Use it for
Download	Let visitors download chatbot transcripts as TXT or PDF.
Consent	Require visitors to accept a notice before they can start chatting.
Fullscreen	Show the fullscreen button.
Sidebar	Show conversation history for on-page chatbots. Sidebar is disabled in popup mode.
Suggested questions	Show first questions visitors can tap before sending their own message.

Text Labels

Open Chatbot settings > Display > Chat text to change the words visitors see in the chatbot.

Setting	Use it for
Greeting	Main greeting text.
Subgreeting	Secondary greeting text.
Placeholder	Input field placeholder.
Footer	Footer text below the chatbot input.
Typing text	Text shown while the chatbot is generating.
Status text	Text shown while knowledge context is being retrieved.

Security and Privacy

Chatbots use both global security settings and chatbot-level controls. Open AI Puffer > Settings > Security.

Setting	What it does
IP Anonymization	Stores anonymized IP addresses in logs.
Banned Words	Blocks messages that contain configured words or phrases.
Banned IPs	Blocks messages from configured IP addresses.

Set custom block messages for banned words and banned IPs if you want visitors to see specific text. Chatbot logs include conversation messages, usage data, feedback, and metadata needed for history and reporting. Enable IP anonymization if you do not want full IP addresses stored in logs.

Use IP anonymization when you need usage logs without storing full visitor IP addresses.

OpenAI moderation is configured from the OpenAI provider settings.

Open AI Puffer > Settings > AI.
Select OpenAI.
Open Advanced.
Set Moderation to Yes.
Set Moderation Message if you want a custom message when input is blocked.

Moderation applies to chatbot requests that use OpenAI. If the chatbot uses another provider, this setting is skipped.

Limits

Limits control how much a visitor can use this chatbot before AI Puffer stops new messages. AI Puffer checks the visitor’s quota before a chat request starts and records usage after the response. Guests are tracked by session. Logged-in users are tracked on their WordPress account. Leave a quota empty for unlimited usage, or set it to 0 to block that group. Open Chatbot settings > AI behavior > Limits to configure chatbot quota controls.

Setting	Use it for
Quota mode	Use the same quota for all logged-in users or define role-based quotas.
Guest quota	Usage quota for visitors who are not logged in. Empty means unlimited. `0` blocks guests.
User quota	Usage quota for logged-in users when using general quota mode. Empty means unlimited. `0` blocks logged-in users.
Role-based quotas	Usage quota per WordPress role. Empty means unlimited for that role.
Reset period	Never, daily, weekly, or monthly.
Quota reached message	Message shown when the visitor reaches the quota.
Primary button	Optional button shown after the quota message.
Secondary button	Optional second button shown after the quota message.

Quota buttons can link to customer dashboard usage, credits, purchases, the buy credits page, a custom URL, or no button.

For credit-based chatbot access, define pricing rules in Usage. To sell prepaid credits, create WooCommerce credit packages in Usage.

Connected Apps

Use Connected Apps to send chatbot events to external apps.

Connected Apps has two parts: a connection stores the app credentials, and a recipe decides which chatbot event is sent to that app.

Connected app recipes can send chatbot data to external services. Map only the fields that the destination app needs.

Chatbot recipes can run on these events:

Event	When it runs
Chat Session Started	The first user message starts a new chat session.
Chat User Message Submitted	A visitor sends a message.
Chat Response Generated	The chatbot finishes an answer.
Chat Feedback Submitted	A visitor submits feedback.
Chatbot Form Submitted	A visitor submits a form displayed by a chatbot rule.

Use Chatbot Form Submitted for forms created with a chatbot rule’s Display form action. Use AI Form Submitted only for standalone AI Forms from the AI Forms module. Open AI Puffer > Settings > Apps to create connections and recipes.

Open Chatbot settings > Automations > Apps to review the recipes attached to the current chatbot.

Failed deliveries appear under Settings > Apps > Delivery Issues, where you can retry or clear them.

Slack

Use Slack to send chatbot messages, responses, feedback, or session alerts to a channel.

Go to https://api.slack.com/apps.
Click Create New App.
Choose From scratch.
Enter an app name and select the workspace.
Click Create App.
Choose one connection method:
- Bot token: open OAuth & Permissions, scroll to Bot Token Scopes, click Add an OAuth Scope, add chat:write, click Install to Workspace, then copy the Bot User OAuth Token that starts with xoxb-.
- Incoming webhook: open Incoming Webhooks, turn on Activate Incoming Webhooks, click Add New Webhook to Workspace, select a channel, then copy the webhook URL.
If you use a bot token, invite the Slack app to the target channel.
In WordPress, open AI Puffer > Settings > Apps.
Create a Slack connection.
Select Token or Webhook.
For Token, enter the Bot Token and Default Channel.
For Webhook, enter the Webhook URL.
Save the connection.
For token connections, click Test Connection. AI Puffer posts a temporary Slack message and removes it after the channel is verified.
Create a recipe, choose a chatbot event, choose Slack Message, map the fields, and enable it.
Scope the recipe to all chatbots or one chatbot.
Test from the frontend chatbot.

Webhook connections are tested at delivery time. If a token test fails, check that the bot is in the default channel.

HubSpot

Use HubSpot to create or update contacts from chatbot events when your recipe maps an email address.

Go to https://app.hubspot.com and select your HubSpot account.
Open Development > Legacy apps.
Click Create private app.
Enter an app name.
Open Scopes.
Add crm.objects.contacts.read and crm.objects.contacts.write.
Create the app.
Open the app’s Auth tab and copy the private app access token.
In WordPress, open AI Puffer > Settings > Apps.
Create a HubSpot connection.
Enter the Private App Token.
Add the Portal ID if you want it stored with the connection.
Save the connection.
Click Test Connection.
Create a recipe, choose a chatbot event, choose HubSpot Contact, map Email, and map any other contact fields you need.
Enable the recipe and test from the frontend chatbot.

HubSpot contact recipes require an email mapping. For lead forms shown inside the chatbot by a rule, choose the Chatbot Form Submitted event. Common mappings are:

HubSpot field	Source path
Email	`data.inputs.email`
First name	`data.inputs.first_name`
Last name	`data.inputs.last_name`
Phone	`data.inputs.phone`
Company	`data.inputs.company`
Note	`data.summary`

Notion

Use Notion to create pages or database items from chatbot events.

Go to https://www.notion.com/my-integrations.
Click New integration or Create a new integration.
Select the workspace and enter an integration name.
Open the integration’s Configuration tab.
Copy the Internal Integration Secret.
In Notion, open the page or database AI Puffer should write to.
Click the … menu in the top-right corner.
Select Connections.
Click + Add connection.
Search for your integration and select it.
Confirm access.
Copy the parent page ID or database ID from the Notion URL.
In WordPress, open AI Puffer > Settings > Apps.
Create a Notion connection.
Enter the Integration Token.
Enter Parent Page ID for page recipes, or Database ID for database item recipes.
Save the connection.
Click Test Connection.
Create a recipe, choose a chatbot event, choose Notion Page or Notion Database Item, map the fields, and enable it.
Test from the frontend chatbot.

The connection test checks the token. If delivery fails, confirm the target page or database is shared with the Notion integration.

Pipedrive

Use Pipedrive to create or update people from chatbot events when your recipe maps a name.

Go to https://app.pipedrive.com.
Open your account menu in the top-right corner.
Open Personal preferences.
Open the API tab.
Copy your personal API token.
Copy your company domain from the browser address. For https://example.pipedrive.com, the company domain is example.
In WordPress, open AI Puffer > Settings > Apps.
Create a Pipedrive connection.
Enter the API Token and Company Domain.
Add Default Owner ID or Pipeline ID if your workflow needs them.
Save the connection.
Click Test Connection.
Create a recipe, choose a chatbot event, choose Pipedrive Person, map Name, and map any other fields you need.
Enable the recipe and test from the frontend chatbot.

Pipedrive person recipes require a name mapping. If an email is mapped, AI Puffer looks for an existing person before creating a new one.

Zapier

Use Zapier when you want to send chatbot event data into a Zap.

Go to https://zapier.com/app/editor.
Click the Trigger step.
Search for Webhooks by Zapier.
Select Webhooks by Zapier.
Set Event to Catch Hook.
Click Continue.
In the Test tab, click Copy to copy the webhook URL.
In WordPress, open AI Puffer > Settings > Apps.
Create a Zapier connection.
Enter the Webhook URL.
Add a Zap Name if you want a label for the connection.
Save the connection.
Create a recipe, choose a chatbot event, choose Zapier Webhook, map the fields, and enable it.
In Zapier, keep the Zap ready to receive a test request.
Test from the frontend chatbot and confirm the request appears in Zapier.

Zapier connections are verified when AI Puffer sends the first event.

Make

Use Make when you want chatbot events to start a Make scenario.

Go to https://www.make.com/en/login and open Make.
Create a new scenario.
Click the large + button.
Search for Webhooks.
Select Webhooks > Custom webhook.
Click Create a webhook.
Name the webhook and save it.
Copy the generated webhook URL.
In WordPress, open AI Puffer > Settings > Apps.
Create a Make connection.
Enter the Webhook URL.
Add a Scenario Name if you want a label for the connection.
Save the connection.
Create a recipe, choose a chatbot event, choose Make Webhook, map the fields, and enable it.
In Make, click Run once so the scenario can receive a test request.
Test from the frontend chatbot and check the Make scenario history.

Make connections are verified when AI Puffer sends the first event.

n8n

Use n8n when you want chatbot events to start an n8n workflow.

Go to https://app.n8n.cloud or open your self-hosted n8n URL.
Create a new workflow.
Add a Webhook node.
Set HTTP Method to POST.
Copy the Test URL if you are testing, or the Production URL if the workflow is active.
In WordPress, open AI Puffer > Settings > Apps.
Create an n8n connection.
Enter the Webhook URL.
Add a Workflow Name if you want a label for the connection.
Save the connection.
Create a recipe, choose a chatbot event, choose n8n Webhook, map the fields, and enable it.
In n8n, click Listen for test event if you used the Test URL, or activate the workflow if you used the Production URL.
Test from the frontend chatbot and check the n8n execution log.

n8n connections are verified when AI Puffer sends the first event.

Rules

Rules run inside a chatbot and can react to chatbot events. A rule runs when its event fires, all of its conditions pass, and its action executes. Lower priority numbers run first. Open Chatbot settings > Automations > Rules, then click Manage rules to create or edit chatbot rules.

Rule Events

Event	When it runs
Session started	A new chatbot session starts with the first user message.
User message received	A visitor sends a message before AI processing.
System error occurred	An internal processing error occurs.
Form submitted	A form displayed by a rule is submitted.

Conditions

Rules can check fields from:

Condition group	Example fields
User context	Logged-in status, user role, user message text.
Text content	User message text.
Conversation state	Message count.
AI model context	Current provider and model.
HTTP context	Referrer and user agent.
Post context	Post ID, title, and tags.
Error context	Error code, error message, failed provider, failed model, status code, operation, and module.

Available operators include equals, contains, starts with, ends with, regex match, empty checks, one-of checks, and numeric comparisons. Conditions inside one rule use AND logic. To run the same action when either of two different conditions is true, create two rules with the same action.

Actions

Action	What it does
Bot reply	Sends a predefined bot message.
Inject context	Adds content to the system instruction or conversation history.
Block message	Stops the user message from reaching the AI.
Call webhook	Sends an HTTP request to an external URL.
Set variable	Stores a variable in user meta or bot context.
Display form	Shows a form inside the chatbot.
Store form submission	Saves submitted form data to the chatbot log.

Webhook and message fields support placeholders. Form placeholders include submitted data, display values, labels, and individual submitted fields.

Webhook actions send data outside WordPress. Use trusted webhook URLs and avoid sending sensitive conversation data unless the destination is meant to receive it.

Example

Lead Collection

Use Display form when the chatbot should ask for contact details inside the conversation. The form is rendered in the chat, and AI processing pauses for that message while the visitor completes it. If the form was displayed from a User Message Received rule, AI Puffer automatically continues the AI response after a successful form submission. It uses the captured user message, adds the submitted form data as context, and avoids resuming when a form-submission rule already returned a direct bot reply. Show the form when the visitor uses a lead keyword:

Add a rule named Lead form.

Set Event to User Message Received.

Add this condition:

Type	Field	Operator	Value
Text Content	User Message Text	Contains	`pricing`

Set Action Type to Display Form.
Add the form title, such as Request a quote.

Add these form elements:

Element	Field ID	Setup
Text Input	`name`	Label: `Name`; required.
Text Input	`email`	Label: `Email`; required.
Dropdown	`budget`	Options such as `Under $1,000`, `$1,000-$5,000`, and `$5,000+`.
Textarea	`message`	Label: `What do you need help with?`

Set Submit Button Text to Send request.

To save the submitted lead in the chatbot log, add a second rule:

Add a rule named Store lead form submission.
Set Event to Form Submitted.
Leave conditions empty if this chatbot only displays one rule form.
Set Action Type to Store Form Submission.
Use this Log Message Format:

Lead form submitted by {{user_name}}. Summary: {{form_submission_summary}}

Make sure the Active checkbox is checked on both rules.

Now ask your bot something about pricing and you will see the form. After the form is submitted, the chatbot continues answering the original pricing question and you can view the submitted details under Usage > Logs. To send the same rule form submission to HubSpot, create a Connected Apps recipe that uses Chatbot Form Submitted and maps fields such as data.inputs.email, data.inputs.first_name, data.inputs.last_name, data.inputs.phone, and data.inputs.company.

​Overview

Live chatbot demo

Deploy

Model

Knowledge

Capabilities

Display

Limits

Connected Apps

Rules

​Create a Chatbot

​Deploy a Chatbot

​On-page Chatbot

​Popup Chatbot

​External Embed

​Model and Instructions

​Knowledge

​Vector

​OpenAI

​Pinecone

​Qdrant

​Chroma

​Results and Minimum Match

​Embedding Models

​Add Knowledge

​Page Context

​Capabilities

​File Upload

​Web Search

​Images and Vision

​Image Analysis

​Image Generation

​Audio and Speech

​Speech to Text

​Text to Speech

​Realtime Voice Agents

​Display

​Widget Colors

​Popup

​Chat Options

​Suggested Questions

​Consent Notice

​Text Labels

​Security and Privacy

​Limits

​Connected Apps

​Slack

​HubSpot

​Notion

​Pipedrive

​Zapier

​Make

​n8n

​Rules

​Rule Events

​Conditions

​Actions

​Example

​Lead Collection

Overview

Create a Chatbot

Deploy a Chatbot

On-page Chatbot

Popup Chatbot

External Embed

Model and Instructions

Knowledge

Vector

OpenAI

Pinecone

Qdrant

Chroma

Results and Minimum Match

Embedding Models

Add Knowledge

Page Context

Capabilities

File Upload

Web Search

Images and Vision

Image Analysis

Image Generation

Audio and Speech

Speech to Text

Text to Speech

Realtime Voice Agents

Display

Widget Colors

Popup

Chat Options

Suggested Questions

Consent Notice

Text Labels

Security and Privacy

Limits

Connected Apps

Slack

HubSpot

Notion

Pipedrive

Zapier

Make

n8n

Rules

Rule Events

Conditions

Actions

Example

Lead Collection