30.1 Overview

AIUNIFY PROS SUITE includes a dedicated Sidebar category titled:

Social Media auto reply

with:

  1. WhatsApp Agent
  2. Instagram Agent
  3. Facebook Agent — Coming Soon

The current Sidebar routes WhatsApp to /social/whatsapp, Instagram to /social/instagram, and identifies Facebook as a Coming Soon feature.

These systems are more than simple Prompt generators. They are persistent communication workspaces designed around connected messaging accounts, stored Agent settings, incoming-message logs, AI-generated replies, and subscriber-controlled automation behavior.

30.2 The Two Active Agents Are Different

Although both automate customer communication, their current operating models are substantially different.

WhatsApp Agent

Provides:

  1. QR-based WhatsApp account linking
  2. Persistent conversation list
  3. Live incoming-message updates
  4. AI auto-replies
  5. Manual replies
  6. New manual chats
  7. AI Persona configuration
  8. All-contact or whitelist targeting
  9. Conversation-level Token statistics

Instagram Agent

Provides:

  1. Manual Instagram Business integration credentials
  2. Scheduled Instagram posts
  3. Manual-URL, AI Image, and AI Reel/Video scheduling
  4. DM auto-reply
  5. Comment auto-reply
  6. DM simulator
  7. Comment simulator
  8. Separate DM and Comment automation rules
  9. Agent Persona settings
  10. Persistent DM/Comment logs

These workflows should not be treated as interchangeable.

30.3 Authentication Is Required

Both Routes use the authenticated PROS SUITE session.

An unauthenticated user is redirected to:

/login.

Part One — WhatsApp Agent

30.4 Opening WhatsApp Agent

Navigate to:

Sidebar → Social Media auto reply → WhatsApp Agent

Route:

/social/whatsapp

30.5 WhatsApp Workspace Name

The workspace is titled:

WhatsApp Agent Control.

30.6 WhatsApp Status Badge

The Header displays:

  1. Linked when connected
  2. Offline otherwise


30.7 Linked Session

When connected, the Header also displays:

Linked to session +[phone number].

30.8 Offline Message

When not connected:

“Connect your mobile device to enable automation and messaging.”

30.9 Main WhatsApp Tabs

The current workspace has two main Tabs:

  1. Active Chats
  2. Agent Settings


30.10 Disconnected Accounts Are Directed Toward Settings

When WhatsApp settings load and the session is not connected, the client automatically switches the workspace to:

Agent Settings.

30.11 Automatic Connection Attempt

The current page also attempts to initiate connection automatically once settings have loaded and the status is disconnected.

Therefore, a subscriber opening an unlinked WhatsApp Agent can be moved directly toward the QR connection workflow.

WhatsApp Connection

30.12 Agent Settings Subtabs

WhatsApp Agent Settings contains three internal sections:

  1. Link & Status
  2. AI Character Persona
  3. Whitelisted Numbers


30.13 Link & Status

The first section contains:

WhatsApp Session Control.

30.14 WhatsApp Connection States

The current UI recognizes states including:

  1. Connected
  2. QR
  3. Connecting
  4. Disconnected

and displays them as:

  1. Active
  2. Scan QR
  3. Starting
  4. Disconnected


30.15 Start Connection

When disconnected, select:

Start Connection.

30.16 Connecting...

While initializing:

Connecting...

may be displayed.

30.17 Initializing Socket

During startup, the interface displays:

Initializing Socket

and:

“Generating secure WhatsApp session handshake. Please wait...”

30.18 QR Code

When the session requires linking, a dynamic:

WhatsApp Web QR Code

is displayed.

30.19 How to Scan the QR Code

The interface instructs:

Open WhatsApp on your mobile phone → Settings → Linked Devices → Link a Device.

30.20 QR Connection Does Not Require a Phone Number Field

Unlike Instagram's credentials workflow, WhatsApp Agent does not ask the subscriber to manually enter account credentials.

The account is linked through the QR session.

30.21 Successfully Connected

After connection, the page displays:

Successfully Connected.

30.22 Connected Phone Number

The connected session can display:

+[phone number]

below Successfully Connected.

30.23 Background Agent Status

The connected-state message says:

“Your AI agent is running successfully in the background and logging interactions.”

30.24 Real-Time Connection Updates

WhatsApp Agent uses a live EventSource connection to receive:

  1. Status changes
  2. QR changes
  3. Message events

without requiring a full page refresh.

30.25 Automatic Live-Update Reconnection

If that live EventSource connection fails, the current client closes it and attempts to reconnect approximately:

6 seconds later.

30.26 Incoming Messages Can Refresh Automatically

When a message event is received, the page refreshes:

  1. Conversation list
  2. Current selected conversation when appropriate


30.27 Unlink Account

When connected, select:

Unlink Account.

30.28 Disconnect Confirmation

WhatsApp asks:

Unlink WhatsApp Account

and:

“Are you sure you want to disconnect? This will log out and unlink your WhatsApp account, stopping all auto-responses.”

30.29 Cancel Unlink

Select:

Cancel

to leave the connection intact.

30.30 Confirm Unlink

Select:

Unlink Account

to proceed.

30.31 Disconnected Confirmation

The current success notification is:

Disconnected

with:

“WhatsApp account unlinked successfully.”

WhatsApp Active Chats

30.32 Active Chats

Select:

Active Chats

to operate the conversation workspace.

30.33 Conversations Panel

The left side is titled:

Conversations.

30.34 Conversation List Is Persistent

The client requests its conversation list from:

/api/social/whatsapp/conversations.

This establishes server-backed conversation history rather than browser-only local chat state.

30.35 Search Conversations

The Search field says:

Search by name or number...

30.36 Search Uses Contact Name or Number

The current filter checks both:

  1. Sender Name
  2. Sender Number


30.37 No Active Conversations Found

If none match:

No active conversations found.

with:

“Click the plus icon above to start chatting manually with a client.”

30.38 Conversation Preview

Each conversation can show:

  1. Contact Name or Phone Number
  2. Last activity time/date
  3. Latest incoming Message
  4. Latest AI reply
  5. Latest manual reply


30.39 AI Reply Preview

If the latest stored entry has an AI response, the list can display:

AI: [reply].

30.40 Manual Reply Preview

A manual outbound entry is shown as:

You: [reply].

Starting a New WhatsApp Chat

30.41 New Manual Chat

Select the Plus icon titled:

New Manual Chat.

30.42 Phone Number Format

The field says:

Enter phone with country code (e.g. 1415...).

30.43 Start

Enter the number and select:

Start.

30.44 Digits Only

When starting a new Chat, the current client removes non-numeric characters before using the number.

30.45 Invalid Number

If no usable digits remain:

Invalid Number

with:

“Please enter digits only.”

30.46 Starting a Chat Does Not Yet Send a Message

The Start action selects or creates a local conversation entry.

The actual outbound WhatsApp Message is not sent until you use the Message composer.

30.47 New Contact

A new locally created conversation can appear with the temporary Name:

New Contact.

WhatsApp Conversation Window

30.48 Selecting a Conversation

Select a contact from the left Conversations list.

The center pane loads that contact's Message history from:

/api/social/whatsapp/messages?contact=[contact].

30.49 Contact Header

The Header displays the selected contact's phone number and current reply mode.

30.50 AI Active

If reply behavior is auto, the Header shows:

AI active

and:

AI Auto-reply On.

30.51 Manual Operator

If the Agent is configured for manual replies:

Manual operator

and:

Manual Mode

are displayed.

30.52 No Chat Selected

If no conversation is selected:

No Chat Selected

with:

“Select a contact from the conversations sidebar or start a new manual chat session using the plus icon.”

30.53 No Messages Recorded

If the selected Chat contains no stored Messages:

No messages recorded in this chat.

and:

“Send a manual reply below to begin the session history.”

30.54 Incoming Messages

Incoming customer Messages appear on the left side of the conversation.

The contact's stored Name can appear above the Message.

30.55 AI Replies

AI-generated replies appear as outbound Messages using the AI styling and an:

AI

Badge.

30.56 Manual Replies

Subscriber/operator replies are visually distinguished and receive a:

Manual

Badge.

30.57 AI Token Badge

An AI reply can show its Token usage inside the Message, for example:

AI (-5T).

30.58 System/Error Messages

Failures can be shown as centered red system Messages.

Manual WhatsApp Replies

30.59 Manual Message Composer

At the bottom of a selected Chat is:

Type a manual reply here...

30.60 Manual Send Requires Connection

The composer and Send action are disabled if the WhatsApp session is not connected.

30.61 Manual Message Delivery

Manual outbound Messages are sent through the WhatsApp session and recorded in the account's WhatsApp logs.

30.62 Manual Messages Use 0 AI Tokens

The current WhatsApp manager records manual outbound Messages with:

tokens_consumed = 0.

This distinguishes an operator-written Message from an AI-generated reply.

30.63 Message Delivery Failed

If a manual Message cannot be transmitted:

Message Delivery Failed

is displayed with the returned Error or:

Failed to transmit manual message.

WhatsApp Conversation Statistics

30.64 Contact Details Panel

On larger screens, the right side shows:

Contact Details

and conversation statistics.

30.65 Total

Total

counts all current stored Message items loaded for that conversation.

30.66 AI Replies

AI Replies

counts Message items classified as auto_reply.

30.67 Tokens Spent

Tokens Spent

adds the tokens_consumed values from the current loaded Messages.

30.68 Manual Count

A Badge displays:

Manual: [number].

30.69 Active Persona Info

The details panel also displays:

Active Persona Info.

30.70 Persona Summary

It can show:

  1. Model
  2. Tone
  3. Personality
  4. Delay


WhatsApp AI Character Persona

30.71 AI Character Persona

Open:

Agent Settings → AI Character Persona.

30.72 AI Persona Identity

The Card is titled:

AI Persona Identity

with:

“Control AI Model parameters, character prompting, tone variables, response delay, and toggle rules.”

30.73 AI Model Orchestrator

The Model selector is labeled:

AI Model Orchestrator.

30.74 Agent Model Is Separate from the Global Header Model

The WhatsApp Agent stores its own model_id.

Changing the general PROS SUITE Header Model should not be treated as the way to change this Agent.

Use the Model selector inside AI Character Persona.

30.75 Model Choices

The dropdown is populated from PROS SUITE's shared:

AVAILABLE_MODELS

collection.

Because that collection can change with the application, the exact live list should be read from the dropdown rather than hardcoded into this manual.

30.76 Initial Model

The page's initial fallback value is:

gemini-2.5-flash.

Stored Agent Settings can override that initial value when loaded.

30.77 Reply Automation Mode

The second selector is:

Reply Automation Mode.

30.78 AI Auto-Reply Enabled

Choose:

AI Auto-Reply Enabled

to permit automatic AI responses when other requirements are also satisfied.

30.79 Manual Operator Control Only

Choose:

Manual Operator Control Only

to prevent AI auto-replies.

30.80 Manual Mode Still Logs Allowed Incoming Messages

When the Agent is active and the incoming contact passes any whitelist rule, Manual Mode records the incoming Message but does not generate an AI reply.

You can then use the WhatsApp conversation composer to respond yourself.

30.81 Tone

WhatsApp provides a free-text:

Tone

field.

Example placeholder:

friendly, casual, sarcastic...

30.82 Personality Type

A second free-text field is:

Personality Type.

Example:

helpful assistant, agent...

30.83 Response Delay

WhatsApp provides:

Response Delay (Seconds).

30.84 Minimum Response Delay

The current numeric field specifies:

min=0.

No maximum is imposed by this visible input.

30.85 Delay Is Applied Before AI Reply Is Sent

The WhatsApp reply manager waits the configured number of seconds after generating the response and before transmitting it.

30.86 System Instruction Prompt

The most important behavior field is:

System Instruction Prompt.

30.87 System Prompt Placeholder

The current placeholder is:

“Describe who the agent is, how they behave, and what information they can supply.”

30.88 What to Put in the System Prompt

A strong System Instruction can define:

  1. Company identity
  2. Agent role
  3. Products/services
  4. Sales behavior
  5. Support boundaries
  6. Approved claims
  7. Escalation instructions
  8. Questions the Agent should ask
  9. Tone
  10. Information it should never invent

30.89 Example System Instruction

A business-focused Prompt could say:

“You are the AIUNIFY customer-engagement assistant. Answer questions about AIUNIFY business software clearly and concisely. Ask prospects what type of business they operate and what systems they need. Never invent pricing or contractual terms. If you do not know an answer, tell the customer a team member will follow up.”

30.90 Critical Persona Implementation Detail

The current incoming-message reply manager directly uses:

  1. system_prompt
  2. model_id
  3. response_delay
  4. Automation/targeting settings

for actual auto-reply processing.

The inspected manager does not directly append the separate Tone and Personality fields to the AI request.

Therefore:

Put mission-critical behavioral instructions directly into the System Instruction Prompt rather than relying only on the Tone and Personality fields.

30.91 Save Configuration

Select:

Save Configuration.

30.92 Settings Saved

Successful persistence produces:

Settings Saved

with:

“WhatsApp AI agent configurations have been successfully updated.”

WhatsApp Whitelisted Numbers

30.93 Target Whitelist Manager

Open:

Whitelisted Numbers

to access:

Target Whitelist Manager.

30.94 Automation Recipient Rules

There are two reply-target options:

  1. Reply to ALL incoming conversations
  2. Only whitelist selected numbers


30.95 Reply to ALL

Choose this when AI automation should be allowed for every incoming contact, subject to the other Agent requirements.

30.96 Only Whitelist Selected Numbers

Choose this when AI automation should apply only to approved phone numbers.

30.97 Add Whitelist Number

The field says:

Add Whitelist Number (digits only, e.g. 14155552671).

30.98 Country Code Recommended

Enter the complete phone number as digits, including the appropriate country code, matching the interface example.

30.99 Adding With Enter

Pressing Enter while focused on the Whitelist field also invokes the add-number action.

30.100 Duplicate Whitelist Entry

If a number already exists:

Already added

with:

“This number is already in the whitelisted targets.”

30.101 Remove a Number

Select the X on a stored Whitelist Badge to remove it from the current list.

30.102 Empty Whitelist

If Select mode is active but there are no numbers:

“No numbers whitelisted. The AI agent will not auto-reply to anyone.”

30.103 Save Target Rules

After modifying targeting, select:

Save Target Rules.

30.104 Important Whitelist Logging Behavior

The WhatsApp reply manager checks the Whitelist before it reaches the normal AI/manual logging branch.

When Select mode is enabled and an incoming number does not match, the manager returns without creating the standard reply log for that Message.

Therefore:

Do not expect the Agent's conversation logs to act as a complete inbox for non-whitelisted contacts when selective targeting is enabled.

30.105 Safety Notice

The Settings area states:

Limits & Safety

and:

“Avoid bulk notifications or spam. Whitelisting targets is recommended to test new configurations safely.”

WhatsApp AI Reply Processing

30.106 Conditions for an Automatic AI Reply

The current reply-processing source requires that:

  1. The Agent exists and is active.
  2. The contact passes Whitelist targeting if Select mode is enabled.
  3. Reply behavior is Auto.
  4. The user has enough Tokens.
  5. AI returns usable content.
  6. The connected WhatsApp session can send it.


30.107 Inactive Agent

If the Agent is inactive or not configured, the current manager does not generate the auto-reply.

30.108 Manual Reply Mode

If manual mode is enabled, the incoming Message is logged with zero AI Tokens and no AI response is sent.

30.109 Insufficient Token Balance

If the account does not have enough Tokens for the auto-reply, the Message is logged as failed with:

Insufficient token balance.

30.110 WhatsApp Auto-Reply Token Cost

The feature catalogue currently identifies:

WhatsApp AI Agent — 5 Tokens.

The reply manager retrieves the configured feature cost and uses:

5

as its fallback.

30.111 When Tokens Are Charged

For a successful AI auto-reply, Tokens are deducted after the AI response is generated and sent.

30.112 Manual Operator Replies Do Not Use AI Reply Tokens

Manual sends are recorded with zero consumed Tokens.

30.113 Auto-Reply Conversation Context

The current WhatsApp reply manager sends the current incoming Message together with the configured System Prompt and selected Model.

It does not source-verify including the full historical conversation log in each AI-generation request.

Therefore:

The current auto-reply engine should not be documented as having persistent multi-turn conversational memory simply because the UI displays historical Messages.

30.114 Message History and AI Memory Are Different

The UI can display persistent conversation history.

That does not mean the AI automatically receives that history as context for its next reply.

30.115 Best Practice for Stateless Replies

Put important business context into the System Prompt so each reply has the core information it needs.

Part Two — Instagram Agent

30.116 Opening Instagram Agent

Navigate to:

Sidebar → Social Media auto reply → Instagram Agent

Route:

/social/instagram

30.117 Workspace Name

The workspace is:

Instagram Agent Control.

30.118 Instagram Status

The Header displays:

Status: @[username] (Active)

when the stored Agent is active.

Otherwise:

Status: Offline.

30.119 Main Instagram Tabs

Current Tabs:

  1. Scheduler
  2. DMs Auto-Reply
  3. Comment Reply
  4. Settings


30.120 Default Instagram Tab

The initial Tab is:

Scheduler.

Instagram Settings and Connection

30.121 Settings

Select:

Settings

to configure the Instagram Agent.

30.122 Agent Profile & Config

The Settings area is titled:

Agent Profile & Config

with:

“Configure AI personality variables, models, response behaviors, and access tokens.”

30.123 Save Agent Config

After making changes, select:

Save Agent Config.

30.124 Settings Saved

The current success message is:

Settings Saved

with:

“Instagram Agent settings have been successfully updated.”

30.125 Instagram Integration Credentials

The connection Card is titled:

Instagram Integration Credentials.

30.126 Instagram Handle

Required field:

Instagram Handle (Username)

with:

e.g. yourbrand_official.

30.127 Instagram Business Account ID

Required field:

Instagram Business Account ID.

30.128 Facebook Page Access Token

Required field:

Facebook Page Access Token.

The field is rendered as a password input.

30.129 No Current OAuth Connect Button

The current user interface does not show a:

Sign in with Instagram

or:

Continue with Facebook

OAuth button.

Subscribers currently enter the required integration credentials directly into the form.

30.130 Connect Account

Select:

Connect Account.

30.131 Connected

After a successful connection response, the current message is:

Connected

with:

“Successfully linked to Instagram account @[username].”

30.132 Disconnect

When a Business Account ID is stored, a:

Disconnect

button is available.

30.133 Disconnected

Current success:

Disconnected

with:

“Instagram account unlinked successfully.”

30.134 Important Instagram Integration Boundary

The sanitized User Operations bundle contains the control surface and Instagram reply-processing manager, but the /api/social/instagram/... Route implementations used by the page were not included in this bundle.

Therefore, this manual can verify:

  1. Which credentials the subscriber enters
  2. Which controls are exposed
  3. How reply-processing logic works in the included manager

but it does not claim to independently audit every external Meta credential-validation, webhook-subscription, or publishing step.

Instagram AI Persona

30.135 AI Persona Variables

The first Settings Card is:

AI Persona Variables.

30.136 AI Model

Instagram Agent has its own:

AI Model

selector.

30.137 Model Choices

Like WhatsApp, the current dropdown is populated from:

AVAILABLE_MODELS.

30.138 Default Instagram Agent Model

The initial local fallback is:

gemini-2.5-flash.

Stored Settings replace it when loaded.

30.139 Instagram Agent Model Is Independent

Use the Model in:

Instagram Agent → Settings

rather than assuming the global PROS SUITE Header Model controls Instagram replies.

30.140 Tone

Instagram provides a fixed Tone selector.

30.141 Tone Choices

Current options:

  1. Friendly
  2. Professional
  3. Witty
  4. Empathetic
  5. Bold
  6. Minimalist


30.142 Default Tone

Initial default:

friendly.

30.143 Personality

Instagram also provides a fixed:

Personality

selector.

30.144 Personality Choices

Current options:

  1. Helpful
  2. Formal
  3. Casual
  4. Sales rep
  5. Expert


30.145 Initial Personality State

The page initializes its local personality state to:

professional

before stored Settings are loaded.

However, professional is not one of the five visible Personality dropdown values shown in the current component.

This is a current source inconsistency.

Stored Settings can replace that initial value.

30.146 System Instruction Prompt

Instagram also exposes:

System Instruction Prompt.

30.147 Critical Instagram Persona Detail

The included Instagram reply manager directly uses:

  1. system_prompt
  2. model_id

when generating DM and Comment replies.

The inspected manager does not directly append the separate Tone and Personality values to those AI requests.

Therefore:

Put critical reply behavior, business rules, and voice requirements directly into System Instruction Prompt.

30.148 Response Delay

Instagram provides:

Response Delay (seconds).

30.149 Instagram Delay Range

The slider is currently:

0–30 seconds.

30.150 Delay Is Applied to Auto-Replies

The reply manager waits the configured delay before completing an automatic DM or Comment response.

Instagram Automation Event Rules

30.151 Automation Event Rules

Settings includes:

Automation Event Rules.

30.152 DM Auto-Reply

The first rule is:

DM Auto-Reply

with:

“Respond to incoming Instagram Direct Messages.”

30.153 DM Modes

Choices:

  1. AI Auto
  2. Manual


30.154 Comment Auto-Reply

The second rule is:

Comment Auto-Reply

with:

“Respond to public comments on your media posts.”

30.155 Comment Modes

Choices:

  1. AI Auto
  2. Manual


30.156 DM and Comment Rules Are Independent

You can configure, for example:

DMs → AI Auto

while:

Comments → Manual

or the reverse.

30.157 No Single Global Auto/Manual Switch

Instagram uses separate DM and Comment behavior settings.

30.158 Manual Mode Means No AI Reply

The included reply manager records incoming DMs or Comments when their respective behavior is Manual but does not generate a response.

30.159 Important Instagram Manual-Mode Limitation

Unlike WhatsApp, the current Instagram Agent page does not provide a manual outbound DM composer or manual Comment-reply form for live operator responses.

Manual mode is therefore source-verified as:

Disable the AI auto-response and retain the item for review/logging

—not as a complete in-app human-response workflow.

Instagram DM Auto-Reply

30.160 DMs Auto-Reply Tab

Select:

DMs Auto-Reply.

30.161 Active DMs

The left pane is titled:

Active DMs.

30.162 Search User

The Search field says:

Search user....

30.163 Conversations Are Built From DM Logs

The page groups stored DM logs by:

sender_username

and orders conversations by their latest logged timestamp.

30.164 Auto-Select First DM

When logs exist and no conversation is selected, the page selects the first conversation automatically.

30.165 No Simulated Chats Found

If none exist:

“No simulated chats found. Send a message on the simulator to start!”

30.166 DM Conversation View

The center pane displays:

  1. Incoming customer Message
  2. AI reply when present
  3. Timestamp
  4. AI Token Badge
  5. Failure/system information


30.167 AI Token Indicator

An outbound AI DM can display:

AI (-[tokens]T).

30.168 Static “AI Reply Auto-active” Label

The DM conversation Header currently displays:

AI Reply Auto-active.

This text is static in the current component.

Because DMs can actually be configured to Manual, do not use this Header text as the authoritative automation setting.

Use:

Settings → DM Auto-Reply

instead.

DM Sandbox Simulator

30.169 DM Sandbox Simulator

The right-side panel is:

DM Sandbox Simulator.

30.170 Purpose

The interface explains:

“Test your AI auto-replies instantly by sending simulated direct messages as a customer.”

30.171 Simulator Client Name

Field:

Simulator Client Name (Username)

with:

e.g. fashion_influencer.

30.172 Username Normalization

The simulator converts its username field to lowercase and removes characters outside:

  1. a–z
  2. 0–9
  3. underscore


30.173 Incoming DM Text

Field:

Incoming DM Text

with:

“Type message as the client...”.

30.174 Send Message as Customer

Select:

Send Message as Customer.

30.175 AI Processing...

During the simulated request:

AI Processing...

is displayed.

30.176 Simulation Success

Current notification:

Simulated message processed

with:

“Check the conversation bubble for response.”

30.177 Simulator Help Text

The page states:

“Clicking send hits the simulator API, generates a response with your prompt, charges 5 tokens, and updates logs.”

30.178 Token Qualification for Simulator

The underlying reply manager retrieves the Instagram Agent feature cost and uses:

5 Tokens

as fallback for a successful AI response.

Manual/inactive processing can log without generating an AI reply and without charging those AI-response Tokens.

30.179 Instagram Agent Catalogue Cost

The feature catalogue lists:

Instagram AI Agent — 5 Tokens.

30.180 DM Auto-Reply Token Condition

Before generating an automatic DM response, the manager checks whether the subscriber has sufficient balance.

30.181 Insufficient DM Tokens

When balance is insufficient, the DM is logged as failed with:

Insufficient token balance.

30.182 DM Reply Context

The current manager sends:

  1. System Prompt
  2. Current incoming DM

to the configured Model.

30.183 No Source-Verified DM Conversational Memory

Historical DM logs are not added to the current reply-generation request in the inspected manager.

Therefore, DM conversation display and AI conversational memory should not be treated as the same feature.

Instagram Comment Auto-Reply

30.184 Comment Reply Tab

Select:

Comment Reply.

30.185 Select Post

The left pane begins with:

Select Post.

30.186 Published Posts Only

The Comment workspace currently lists only Posts whose system status is:

published.

30.187 No Published Posts

If none are available:

“No published posts found. Go to Scheduler to publish a post first.”

30.188 Comment Thread

After selecting a Post, the center pane displays:

Comment Thread.

30.189 Comment Log Contents

Each stored Comment can display:

  1. Commenter username
  2. Time
  3. Comment Text
  4. AI auto-reply
  5. Tokens consumed
  6. Failure
  7. Manual-review status


30.190 AI Auto-Reply Label

Automatic Comment responses display:

AI Auto-reply.

30.191 Comment Token Badge

The reply can display:

-[tokens]T.

30.192 Manual Review

When no AI reply is present and the record is not an Error:

Manual review (AI reply offline).

30.193 Comment Failure

A failed reply can display:

Auto-reply failed: [error].

Comment Sandbox Simulator

30.194 Comments Sandbox Simulator

The right pane is:

Comments Sandbox Simulator.

30.195 Purpose

The interface states:

“Simulate incoming user comments on your published posts to test the AI's automated thread responses.”

30.196 Select a Published Post First

The simulator requires a selected published Post.

Without one:

“Please select a published post first to enable comment simulations.”

30.197 Simulator Commenter Username

Field:

Simulator Commenter Username

with:

e.g. food_blogger.

30.198 Comment Text

Field:

Comment Text

with:

“Write a comment on the selected post...”.

30.199 Simulate Comment Reply

Select:

Simulate Comment Reply.

30.200 AI Replying...

During processing:

AI Replying...

30.201 Simulation Success

Current message:

Comment reply simulated

with:

“AI auto-reply added to comment logs.”

30.202 Comment Reply Is Designed to Be Short

The current Instagram reply manager instructs the AI to respond to a Comment in:

1–2 sentences

and to keep it:

  1. Brief
  2. Conversational
  3. Appropriate for a social-media Comment thread


30.203 Comment Context

The AI receives:

  1. Post Caption
  2. Current Comment
  3. System Prompt

for the Comment reply.

30.204 No Full Comment-Thread Memory

The inspected Comment reply function does not source-verify sending previous Comment-thread Messages into each generation.

30.205 Comment Token Charge

Successful automatic Comment replies use the Instagram Agent feature cost, currently falling back to:

5 Tokens.

Instagram Scheduler

30.206 Scheduler

Instagram Agent includes a complete:

Scheduler

workspace.

30.207 Scheduled Post Queue

The Header is:

Scheduled Post Queue

with:

“Create, monitor, and publish scheduled images and reels.”

30.208 No Posts Scheduled

Empty state:

No posts scheduled

and:

“Get started by clicking the ‘Schedule Post’ button and scheduling media content.”

30.209 Schedule Post

Select:

Schedule Post.

30.210 Schedule New Instagram Post

The modal is titled:

Schedule New Instagram Post

with:

“Queue an image or reel with a caption and date-time.”

30.211 Media Content Source

The current Scheduler supports three sources:

  1. Manual URL
  2. AI Image
  3. AI Reel/Video


Manual URL Scheduling

30.212 Manual URL

The default media-source mode is:

Manual URL.

30.213 Media Image URL

The field is labeled:

Media Image URL *.

30.214 Public Image or Video URL

Despite the “Image URL” label, the helper says:

“Use a public Unsplash/web image or video URL.”

Therefore, the current Manual URL workflow is intended to accept public media URLs for either Images or Videos.

30.215 Manual File Upload Is Not Provided

The Scheduler modal does not expose a local:

Upload Image

or:

Upload Video

control.

Manual scheduling uses a URL.

AI Image Scheduling

30.216 AI Image

Select:

AI Image

as the Media Content Source.

30.217 Image Generation Prompt

Field:

Image Generation Prompt *.

30.218 Produce with AI Generator

Select:

Produce with AI Generator.

30.219 Scheduler AI Image Configuration

The Scheduler's AI Image workflow currently uses fixed:

  1. 1:1 size
  2. Enhancement enabled


30.220 No AI Image Ratio Selector in Scheduler

The Scheduler modal does not expose Image:

  1. Aspect Ratio
  2. Style
  3. Resolution

controls.

Its Image generation currently uses 1:1 automatically.

30.221 AI Production Started

Current message:

AI Production Started

with:

“Media is rendering. Please wait...”

30.222 AI Image Polling

The Scheduler checks AI Image status approximately every:

5 seconds.

30.223 AI Image Ready

Success:

AI Image Ready

with:

“Visual successfully generated and attached to schedule.”

AI Reel/Video Scheduling

30.224 AI Reel/Video

Select:

AI Reel/Video.

30.225 Video/Reel Vision Prompt

The Prompt field changes to:

Video/Reel Vision Prompt *.

30.226 Scheduler Reel Defaults

The current Scheduler-generated Reel uses fixed settings:

  1. Ratio: 9:16
  2. Resolution: 480p
  3. Duration: 6 seconds
  4. Mode: normal
  5. Random internal Seed


30.227 No Reel Settings Panel Inside Scheduler

The Scheduler does not expose controls for changing those fixed Reel parameters.

For more detailed Reel configuration, use the dedicated Reels Generator described in Chapter 27.

30.228 AI Reel Ready

When completed:

AI Reel Ready

with:

“Video successfully generated and attached to schedule.”

30.229 AI Generator Active

During AI media production, the modal displays:

AI Generator Active.

30.230 Scheduler Time Estimate

The interface says:

“This can take 15-30 seconds.”

This should be treated as interface guidance, not a guaranteed processing duration.

30.231 Generated Media Preview

Once AI media is ready, the modal displays:

Generated Media Preview.

30.232 Remove Generated Media

The X on the Generated Media Preview removes that media from the current scheduling form.

30.233 Removing Preview Does Not Delete the AI Asset

The current action clears the Scheduler's selected URLs.

It is not source-verified as deleting the underlying Marketing Asset record.

30.234 Closing Scheduler During AI Generation

Closing the modal clears the Scheduler's browser polling interval.

This does not source-verify cancellation of the already-started server-side AI media task.

Instagram Caption and Schedule Time

30.235 Post Caption

The scheduling form includes:

Post Caption.

30.236 Caption Is Optional

The current client requires media and publication time, but does not require Caption.

30.237 Emojis and Hashtags

The placeholder states:

“Write caption (emojis and hashtags are supported)...”

30.238 Publication Date & Time

Required:

Publication Date & Time *.

The browser uses a datetime-local input.

30.239 Missing Scheduling Information

If media or scheduled time is absent:

Missing Info

with:

“Please specify media content (or generate with AI) and publication time.”

30.240 Queue Schedule

Select:

Queue Schedule.

30.241 Scheduling...

While submitting:

Scheduling...

30.242 Post Scheduled

Success:

Post Scheduled

with:

“Post queued successfully.”

30.243 Scheduled Post Card

A Scheduler Card can display:

  1. Image/Video Preview
  2. Caption
  3. Schedule/Published time
  4. Status
  5. Error Message


30.244 Post Statuses

Current statuses include:

  1. Scheduled
  2. Published
  3. Failed


30.245 Scheduled Time

A scheduled Post displays:

Schedule: [date/time].

30.246 Published Time

A published Post displays:

Published: [date/time].

30.247 Failed Post

If a Post contains an Error Message, that Error appears on the Card.

Canceling a Scheduled Post

30.248 Cancel Schedule

A Trash action appears only for Posts whose status is:

scheduled.

30.249 Post Canceled

Current success:

Post Canceled

with:

“Post has been removed from the schedule.”

30.250 Published Posts Cannot Be Canceled Through This Control

The Delete/Cancel icon is rendered only for scheduled entries.

30.251 No Edit Scheduled Post Control

The current Scheduler Cards do not provide:

  1. Edit Caption
  2. Replace Media
  3. Change Time
  4. Reschedule

To change a scheduled item, the current user-facing approach is to cancel it and create another schedule entry.

Run Cron

30.252 Run Cron

The Scheduler Header includes:

Run Cron.

30.253 What Run Cron Does

This user-facing control calls the Scheduler processing endpoint to process due Posts.

30.254 Scheduler Executed

Successful execution produces:

Scheduler Executed

with:

“Processed [number] due posts. Check logs for status updates.”

30.255 Why Run Cron Is Unusual

“Cron” is a technical scheduler term, but it is currently exposed directly to subscribers.

Operationally, treat it as:

Run the due-post processing cycle now.

30.256 Normal Scheduling Does Not Require Repeated Manual Clicking

The existence of Run Cron does not itself prove that subscribers must manually run it for every Post.

The API/Scheduler infrastructure responsible for automatic production execution is outside the sanitized Route bundle.

Use Run Cron as a visible manual processing/testing control rather than assuming it replaces all scheduled background execution.

Instagram Token Behavior

30.257 Auto-Reply Cost

The current catalogue identifies:

Instagram AI Agent — 5 Tokens.

30.258 DM Replies

A successful automatic DM response uses the configured feature cost, with a current fallback of:

5 Tokens.

30.259 Comment Replies

A successful automatic Comment response similarly uses the Instagram Agent feature cost.

30.260 Manual Mode

Incoming DMs or Comments processed under Manual behavior are logged without an AI response and with zero AI-reply Tokens in the current manager.

30.261 Scheduler AI Media Is Separate

The AI Image and AI Reel/Video creation features inside Scheduler use:

/api/marketing

rather than the Instagram Agent's DM/Comment reply function.

Therefore:

Do not assume the Instagram Agent's 5-Token auto-reply cost is also the complete cost of generating Scheduler Images or Reels.

Those are separate Marketing-generation operations.

30.262 No Token Cost Is Displayed Beside Scheduler AI Media

The Scheduler modal does not show a fixed media-generation Token price.

Instagram Model/API Behavior

30.263 Agent Model Is Stored Per Instagram Agent

Instagram Settings store:

model_id

separately from the global PROS SUITE Model selection.

30.264 Server-Side Agent Provider Credentials

The included Instagram reply manager uses server/environment provider credentials for its selected Model pathways rather than receiving the subscriber's standard BYOK headers from the Agent page.

30.265 Chapter 11 BYOK Is Not the Same Control

Accordingly, the subscriber's general API-Key settings should not be described as the direct configuration mechanism for Instagram Agent auto-replies in the current source.

Shared AI-Reply Limitations

30.266 Historical Logs Do Not Equal AI Memory

Both Agents maintain historical logs in their interfaces.

However, the included auto-reply managers generate a response from the current incoming Message plus configured instructions/model, rather than source-verifiably feeding the whole visible conversation into every request.

30.267 Avoid Pronoun-Only Follow-Ups

Because persistent conversational memory is not source-verified, instructions and customer flows should not depend heavily on the AI automatically understanding references such as:

“What about the other one?”

without enough current context.

30.268 Put Core Business Facts in System Instructions

Include the important reusable information the Agent needs.

30.269 Do Not Put Secrets in System Instructions

Avoid entering:

  1. Passwords
  2. Private API keys
  3. Sensitive internal credentials

into conversational Agent Prompts.

Facebook Agent

30.270 Facebook Agent

The Sidebar currently displays:

Facebook Agent

under Social Media auto reply.

30.271 Coming Soon

The Facebook entry is explicitly marked:

isComingSoon: true.

30.272 Facebook Agent Is Not Documented as Operational

No matching app/social/facebook/page.tsx source was found in the inspected subscriber source bundle, while the Sidebar explicitly identifies the entry as Coming Soon.

Therefore this chapter does not invent:

  1. Facebook login
  2. Messenger auto-replies
  3. Facebook Comment replies
  4. Page posting
  5. Scheduling
  6. Agent configuration

for the current version.

WhatsApp Best Practices

30.273 Test With Manual Mode First

Before enabling AI Auto-Reply broadly:

  1. Link the WhatsApp account.
  2. Configure System Instruction Prompt.
  3. Choose the Model.
  4. Use Manual Operator mode.
  5. Confirm incoming Messages are logging correctly.
  6. Test controlled contacts.
  7. Enable AI Auto when satisfied.

30.274 Use the Whitelist for Controlled Testing

The interface itself recommends Whitelisting as a safe testing method.

30.275 Start With Your Own Test Number

A practical rollout pattern is:

Only whitelist selected numbers → Add a controlled test number → Verify responses → Expand carefully.

30.276 Avoid “Reply to ALL” Until the Prompt Is Ready

A poorly configured System Prompt applied to all inbound conversations can create undesirable customer responses.

30.277 Define Escalation Rules

Tell the Agent when it should avoid guessing.

Example:

“If a prospect asks for custom enterprise pricing, tell them an AIUNIFY representative will follow up rather than inventing a quote.”

30.278 Define Sales Qualification

For a sales-oriented Agent, instruct it to ask useful questions such as:

  1. Industry
  2. Team size
  3. Business need
  4. Current system
  5. Desired outcome

30.279 Keep Response Delay Natural

A small delay may make automated replies feel less instantaneous.

Long delays can negatively affect responsiveness.

30.280 Monitor Tokens Spent

Use conversation-level:

Tokens Spent

to understand AI usage for individual WhatsApp interactions.

30.281 Use Manual Reply for Sensitive Conversations

Switch to Manual Operator mode for interactions requiring:

  1. Contract negotiation
  2. Complaints
  3. Billing disputes
  4. Legal issues
  5. Sensitive personal information
  6. High-value sales decisions

Instagram Best Practices

30.282 Configure DM and Comment Behavior Separately

DMs and Comments often require different communication styles.

For example:

DMs

More conversational and qualification-oriented.

Comments

Short, public, brand-safe responses.

30.283 Use the Sandbox Before Auto Mode

Use:

  1. DM Sandbox Simulator
  2. Comments Sandbox Simulator

before trusting automatic customer-facing behavior.

30.284 Remember Simulators Can Consume Tokens

The DM simulator explicitly states that its generated AI response is charged as Agent usage.

30.285 Keep Public Comment Replies Short

The current backend specifically prompts for 1–2 sentence Comment responses.

30.286 Put Public-Reply Boundaries in System Prompt

For example:

“Never discuss confidential account information in public Comments. Invite the customer to DM us when account-specific help is needed.”

30.287 Review Scheduler Media Before Queueing

When generating AI media inside the Scheduler:

  1. Generate media.
  2. Inspect Preview.
  3. Remove it if unsuitable.
  4. Generate another if necessary.
  5. Only then Queue Schedule.

30.288 Verify Generated Media Text

As with other AI Image/Reel Tools, visually verify:

  1. Brand Name
  2. Offer text
  3. Product appearance
  4. Logos
  5. Faces
  6. Written text

30.289 Verify Publication Date and Time

The Scheduler uses a local browser datetime-local field.

Always confirm the displayed intended date/time before Queue Schedule.

30.290 Check Failed Posts

A failed scheduled Post can show its Error Message in the queue.

Do not assume every queued item was successfully published.

Troubleshooting — WhatsApp

30.291 WhatsApp Agent Opens Offline

Go to:

Agent Settings → Link & Status

and start/review the connection.

30.292 QR Code Does Not Appear Immediately

The session can pass through:

Starting / Initializing Socket

before the QR state appears.

30.293 QR Code Appears

On your phone:

WhatsApp → Settings → Linked Devices → Link a Device

and scan it.

30.294 WhatsApp Is Connected but AI Does Not Reply

Check:

  1. Reply Automation Mode is AI Auto-Reply Enabled.
  2. Agent is active/connected.
  3. Whitelist targeting permits the number.
  4. Token balance is sufficient.
  5. System Prompt and Model are valid.

The backend checks these conditions before replying.

30.295 Incoming Contact Is Not in Whitelist

If Select targeting is enabled, non-matching contacts are skipped before normal reply processing.

30.296 Select Mode Has No Numbers

The UI explicitly warns:

“The AI agent will not auto-reply to anyone.”

30.297 AI Reply Shows Insufficient Balance

The Manager logs:

Insufficient token balance

when the account cannot cover an AI reply.

30.298 Manual Send Button Is Disabled

Manual sending requires:

  1. A selected conversation
  2. Non-empty Message
  3. Connected WhatsApp session


30.299 New Chat Number Is Rejected

Enter digits only, including country code.

30.300 Conversation Does Not Update

The page uses live EventSource updates and automatically attempts reconnect after an EventSource Error.

If necessary, re-enter/reload the workspace so conversations and Messages are fetched again.

Troubleshooting — Instagram

30.301 Instagram Shows Offline

Go to:

Settings → Instagram Integration Credentials

and review:

  1. Username
  2. Instagram Business Account ID
  3. Facebook Page Access Token

30.302 Connection Failed

The current UI displays:

Connection Failed

with the returned Error.

Because the integration API Route is outside the sanitized bundle, use the returned Error as the primary current diagnostic.

30.303 DM Says AI Reply Auto-active but Settings Are Manual

The conversation Header text is static.

Use:

Settings → DM Auto-Reply

as the actual current configuration.

30.304 Manual Instagram DM Mode Has No Reply Composer

That is a current UI limitation.

Manual mode logs the incoming DM but does not provide a manual-send box on this page.

30.305 Manual Comment Mode Has No Reply Composer

Likewise, there is no in-page human Comment-response composer in the current source.

30.306 No Published Post Appears in Comment Tab

The Comments pane only lists system Posts whose status is published.

Check the Scheduler queue.

30.307 Comment Simulation Button Is Disabled

Select a published Post first and enter Comment Text.

30.308 AI Scheduler Image Is the Wrong Ratio

The embedded Scheduler AI Image workflow is currently fixed to:

1:1.

Use the dedicated Image Generator when you need more ratio choices.

30.309 AI Scheduler Reel Is the Wrong Format

The embedded Scheduler Reel generation is fixed to:

  1. 9:16
  2. 480p
  3. 6 seconds
  4. Normal


Use the dedicated Reels Generator for more control.

30.310 Cannot Upload a Local File in Scheduler

The current manual source input is a URL.

No direct local file-upload control is source-verified.

30.311 Cannot Edit Scheduled Post

No Edit/Reschedule action exists on current Post Cards.

Cancel the scheduled item and create a new one when necessary.

30.312 Scheduled Post Failed

Review the Error shown on its Post Card.

30.313 Run Cron Shows Zero Processed

The control reports the number of due Posts it processed.

A value of zero can simply mean there were no currently due Posts for that processing cycle.

WhatsApp Setup Checklist

30.314 Connection Checklist

  1. I opened WhatsApp Agent.
  2. I opened Link & Status.
  3. I started the connection.
  4. I scanned the QR with Linked Devices.
  5. Status shows Active/Linked.
  6. Correct phone number appears.
  7. I understand Unlink Account stops auto-responses.

30.315 Persona Checklist

  1. Correct AI Model is selected.
  2. Reply Automation Mode is correct.
  3. Tone is reviewed.
  4. Personality is reviewed.
  5. Response Delay is appropriate.
  6. System Instruction Prompt defines the business clearly.
  7. I saved the configuration.
  8. Critical behavioral instructions are contained in the System Prompt.

30.316 Whitelist Checklist

  1. I chose ALL or selected-number mode.
  2. If testing, I selected Whitelist mode.
  3. Numbers include appropriate country codes.
  4. No duplicate numbers exist.
  5. I saved Target Rules.
  6. I understand non-whitelisted Messages can be skipped by Agent logging.

30.317 WhatsApp Auto-Reply QA Checklist

  1. Agent is connected.
  2. Auto mode is active.
  3. Test contact passes targeting.
  4. Token balance is sufficient.
  5. Test Message receives appropriate response.
  6. Response Delay behaves as expected.
  7. No unsupported claims appear.
  8. Escalation rules work.
  9. Conversation log records the interaction.
  10. Token usage appears correctly.

Instagram Setup Checklist

30.318 Connection Checklist

  1. Instagram Handle is correct.
  2. Business Account ID is correct.
  3. Facebook Page Access Token is entered.
  4. Connect Account succeeded.
  5. Header shows Active.
  6. I know how to Disconnect if needed.

30.319 Instagram Persona Checklist

  1. Agent Model is selected.
  2. Tone is selected.
  3. Personality is selected.
  4. System Prompt contains all critical business behavior.
  5. Response Delay is appropriate.
  6. DM Auto-Reply is Auto or Manual as intended.
  7. Comment Auto-Reply is Auto or Manual as intended.
  8. I selected Save Agent Config.

30.320 DM Testing Checklist

  1. I opened DMs Auto-Reply.
  2. I entered a test username.
  3. I entered a realistic incoming DM.
  4. I selected Send Message as Customer.
  5. I reviewed the AI response.
  6. I checked Token usage.
  7. I tested common customer questions.
  8. I tested situations the AI should escalate.
  9. I understand the simulator can consume Agent Tokens.

30.321 Comment Testing Checklist

  1. At least one system Post is Published.
  2. I selected that Post.
  3. I entered a test Commenter username.
  4. I entered Comment Text.
  5. I selected Simulate Comment Reply.
  6. AI response is concise.
  7. Response fits a public thread.
  8. No private information is disclosed.
  9. Token usage is acceptable.

30.322 Scheduler Checklist

  1. I opened Scheduler.
  2. I selected Manual URL, AI Image, or AI Reel/Video.
  3. Media is available.
  4. AI-generated media has been reviewed.
  5. Caption is correct.
  6. Hashtags/emojis are correct.
  7. Publication Date & Time is correct.
  8. I selected Queue Schedule.
  9. Post appears as Scheduled.
  10. I later confirm Published or Failed status.

WhatsApp vs. Instagram Matrix

30.323 Current Capability Comparison

CapabilityWhatsApp AgentInstagram Agent
Authenticated PROS pageYesYes
Account connectionQR / Linked DevicesBusiness ID + Page Access Token
Persistent inbound logsYesYes
AI auto-replyYesYes
Manual-mode loggingYesYes
Manual outbound reply inside AgentYesNo current composer
New manual conversationYesNo
DM auto-replyWhatsApp MessagesYes
Public Comment auto-replyNoYes
Reply WhitelistYesNo
Response DelayYesYes
Agent-specific ModelYesYes
System Instruction PromptYesYes
ToneFree textPreset selector
PersonalityFree textPreset selector
SchedulerNoYes
AI Image schedulingNoYes
AI Reel schedulingNoYes
Sandbox DM simulatorNo dedicated simulatorYes
Comment simulatorNoYes
Conversation Token statisticsYesReply-level badges/logs
Current Agent fallback cost5 Tokens5 Tokens

30.324 Auto-Reply Context Matrix

ContextCurrent AI Input Source
WhatsApp ReplySystem Prompt + current incoming Message
Instagram DM ReplySystem Prompt + current incoming DM
Instagram Comment ReplySystem Prompt + Post Caption + current Comment

The inspected reply managers do not establish full historical-conversation context on every generation.

30.325 What WhatsApp Agent Currently Supports

The current source verifies:

Connection

  1. QR linking
  2. Linked Devices instructions
  3. Connected/Disconnected state
  4. Automatic connection attempt
  5. Live connection updates
  6. Unlink workflow

Messaging

  1. Persistent conversations
  2. Persistent Message history
  3. Conversation Search
  4. New manual Chat
  5. Manual outbound text Message
  6. AI auto-reply
  7. Manual operator mode
  8. AI/manual visual distinction
  9. Message failure display
  10. Live Message updates

AI Configuration

  1. Agent-specific Model
  2. Tone
  3. Personality
  4. Response Delay
  5. System Instruction Prompt
  6. Auto vs. Manual

Targeting

  1. Reply to all
  2. Selected-number Whitelist
  3. Add/remove numbers

Usage

  1. 5-Token current auto-reply feature cost
  2. Conversation Tokens Spent
  3. AI Reply count
  4. Manual Reply count
  5. 0 AI Tokens for manual sends

30.326 What WhatsApp Agent Does Not Currently Establish

The current source does not establish:

  1. Media attachment composer
  2. Image sending from this UI
  3. Video sending from this UI
  4. Audio/voice-note sending
  5. Document attachment
  6. Emoji picker
  7. Message Templates
  8. Scheduled WhatsApp Messages
  9. Broadcast Campaigns
  10. Bulk outbound Messages
  11. Contact import
  12. CRM synchronization controls
  13. Group Chat management
  14. WhatsApp Status posting
  15. AI conversation-memory history in each generation
  16. Subscriber BYOK headers for Agent replies

30.327 What Instagram Agent Currently Supports

The current source verifies:

Integration

  1. Instagram Handle
  2. Instagram Business Account ID
  3. Facebook Page Access Token
  4. Connect
  5. Disconnect
  6. Active/Offline status

AI Persona

  1. Agent-specific Model
  2. Tone choices
  3. Personality choices
  4. System Prompt
  5. 0–30-second delay

DM Automation

  1. Auto or Manual
  2. Stored logs
  3. Conversation grouping
  4. Search
  5. Sandbox Simulator
  6. Token usage display

Comment Automation

  1. Auto or Manual
  2. Published-Post selection
  3. Comment logs
  4. AI reply display
  5. Token usage
  6. Comment Simulator
  7. Short 1–2-sentence AI response logic

Scheduler

  1. Scheduled Post queue
  2. Manual public media URL
  3. AI Image generation
  4. AI Reel/Video generation
  5. Caption
  6. Publication Date & Time
  7. Scheduled/Published/Failed statuses
  8. Cancel scheduled Post
  9. Run Cron
  10. AI generated media Preview

30.328 What Instagram Agent Does Not Currently Establish

The current source does not establish:

  1. OAuth login button
  2. Local file upload in Scheduler
  3. Manual outbound DM composer
  4. Manual Comment-reply composer
  5. Edit scheduled Post
  6. Reschedule Post
  7. Multiple Images/carousel composer
  8. Stories scheduler
  9. Instagram Live
  10. Hashtag analytics
  11. Follower analytics
  12. Engagement analytics
  13. Bulk DM campaign
  14. Contact segmentation
  15. Comment keyword rules
  16. DM keyword-trigger builder
  17. Conversation-memory history in every AI reply
  18. Direct use of subscriber BYOK API headers
  19. Full external Meta webhook/publication implementation audit from this sanitized bundle

30.329 Facebook Agent Current Status

Current Sidebar state:

Facebook Agent — Coming Soon.

No operational subscriber workflow should be documented until a future source version confirms one.

30.330 Chapter Summary

AIUNIFY PROS SUITE currently provides two operationally distinct Social Media Auto Reply systems:

WhatsApp Agent and Instagram Agent.

WhatsApp Agent at:

/social/whatsapp

uses a QR-based account-linking workflow. Subscribers connect their WhatsApp account through Linked Devices, after which the workspace can maintain persistent Conversations, receive live updates, generate AI replies, and allow operator-written manual responses.

Its AI configuration includes:

  1. Agent-specific Model
  2. Auto/Manual response behavior
  3. Tone
  4. Personality
  5. Response Delay
  6. System Instruction Prompt

and it adds a separate Target Whitelist Manager allowing automation for either every incoming conversation or only selected phone numbers.

The current reply manager applies the Whitelist, checks Auto/Manual behavior, validates Token balance, generates the response, applies any configured delay, sends the WhatsApp Message, deducts the Agent usage cost, and logs the result. The current feature cost is 5 Tokens per successful AI auto-reply; manual operator Messages are logged with zero AI Tokens.

Instagram Agent at:

/social/instagram

uses a different setup requiring:

  1. Instagram Handle
  2. Instagram Business Account ID
  3. Facebook Page Access Token

and provides separate controls for DM Auto-Reply and Comment Auto-Reply, each of which can be configured for AI Auto or Manual.

Instagram's DM and Comment workspaces also provide Sandbox Simulators so a subscriber can test the Agent's responses before relying on live customer interactions. The Instagram Agent catalogue cost is currently 5 Tokens, and the included reply manager uses that feature cost for successful AI DM and Comment replies.

One major difference from WhatsApp is that Instagram Manual mode currently disables the AI reply and records the inbound item, but the inspected Instagram page does not provide an in-app manual DM or Comment response composer.

Instagram Agent also contains a Scheduler. Subscribers can queue media using:

  1. Manual URL
  2. AI Image
  3. AI Reel/Video

plus a Caption and Publication Date & Time.

The embedded Scheduler's AI Image generator currently uses fixed 1:1 output, while its AI Reel/Video generator uses fixed 9:16, 480p, 6 seconds, Normal mode, with an internally generated Seed. Those embedded settings are not subscriber-adjustable inside Scheduler.

Scheduled Posts can display:

  1. Scheduled
  2. Published
  3. Failed

statuses, and scheduled Posts can be canceled before publication. The visible Run Cron control manually runs a due-post processing cycle and reports how many due Posts were processed.

A second important limitation applies to both active Agents: their user interfaces maintain historical conversation logs, but the included reply managers do not source-verify sending complete prior conversation history into every AI reply. Current reply generation is based primarily on the configured System Prompt and the current incoming communication, with Instagram Comments additionally receiving the Post Caption.

For that reason, the recommended operating strategy is:

Configure the System Instruction Prompt Carefully → Start in Manual or Whitelist-Limited Testing → Select the Correct Agent Model → Test Typical Customer Questions → Test Unknown/Sensitive Questions → Verify Token Usage → Confirm Escalation Rules → Enable AI Auto-Reply Gradually → Review Conversation Logs Regularly → Move Sensitive or High-Value Conversations to Human Handling When Appropriate

For Instagram:

Connect Account → Configure DM and Comment Behavior Separately → Test Both Simulators → Generate or Supply Scheduled Media → Verify Every Caption and Creative → Queue Schedule → Confirm Published/Failed Status → Review DM and Comment Logs

The third Sidebar entry, Facebook Agent, remains explicitly marked Coming Soon and should not yet be treated as an operational subscriber system.

Write Your Comment