You can receive and reply to your WhatsApp messages directly inside Madyis Hub using Twilio. It takes about 10 minutes. Follow the steps in order. ⚠️ The most important point: unlike some other channels, connecting WhatsApp through Twilio is not fully automatic. You must paste a URL (the "webhook") into Twilio, otherwise incoming messages will never reach Madyis Hub. That is step 3 below, and it is the #1 reason messages "don't show up". Before you start - A Twilio account with WhatsApp enabled (an approved WhatsApp number, or the "Sandbox" for testing). - Your Twilio credentials: Account SID and Auth Token, shown on the Twilio Console home page. Step 1 — Create the inbox in Madyis Hub 1. Go to Inboxes & channels → Add channel → WhatsApp, then choose Twilio. 2. Fill in: - the inbox name (e.g. "WhatsApp Support"); - your WhatsApp number in international format (e.g. +15551234567, no spaces); - your Account SID and Auth Token. 3. Click Create channel. Step 2 — Copy the callback URL Right after creation, Madyis Hub shows a callback URL. You can also find it anytime in the inbox Configuration tab. It looks like: https://madyishub.io/twilio/callback Copy it. This is what tells Twilio where to deliver the messages your customers send you. Step 3 — Paste the URL into Twilio (the step not to skip) In the Twilio Console, open your WhatsApp sender configuration: Messaging → Senders → WhatsApp senders → your number. Find the "Messaging Endpoint Configuration" section and fill in: - Webhook URL for incoming messages: paste the callback URL from step 2. - Webhook method for incoming messages: HTTP Post. - Status callback URL (optional): https://madyishub.io/twilio/delivery_status — to receive delivery receipts (sent / read). - Messaging service: leave empty if you don't use one. Click Save. The "Profile about" field Twilio may ask for is simply the short description of your WhatsApp profile (cosmetic, free text, ~139 characters). For example: "Support — bookings and questions". It has no impact on message delivery. Step 4 — Test From a phone, send a WhatsApp message to your number. Within a few seconds it should appear as a new conversation in the inbox you just created. Special case: the Twilio Sandbox The Sandbox lets you test before you have an approved WhatsApp number: - From your phone, join the Sandbox first: send join <your-code> to the Sandbox number shown by Twilio. - Put the callback URL in the Sandbox settings, field "When a message comes in". - In Madyis Hub, the inbox number must be the Sandbox number (often +14155238886), not your real number. Still not working? - Make sure the callback URL is exact and set to HTTP Post. - Make sure the inbox number matches your Twilio number exactly (international +… format, no spaces). - If you use a Twilio Messaging Service: put the callback URL in that service instead (Integration → Incoming Messages tab), then enter its Messaging Service SID when creating the inbox. - Stuck on a step? Ask the assistant in the bottom-right corner of your dashboard.

🤖 AI Agents

The AI action log: understand replies (and non-replies)

The action log shows, conversation by conversation, what your AI agent did — and why. It's the tool to understand a reply… or the lack of one. Where to find it Open your AI agent → Log tab. What it contains For each generated reply: the model used, the response time, and the knowledge documents used. The log also records sent replies, skipped replies (monthly quota reached, outside the agent's hours…) and any failures. Debugging "why didn't the AI reply" - Quota reached? → the AI skips replying until next month. - Agent's schedule? → check its Availability (24/7, after-hours, or business hours). - A human already replied? → the AI steps back so it doesn't talk over you. - Agent not connected to the inbox? → check the agent's Channels tab. Good to know: the log also shows whether the AI sent the whole knowledge base (small base) or only the relevant passages (large base) — useful to understand its answers.

🤖 AI Agents

Import your help center into your AI agent

Already have a help center? Reuse it to feed your AI agent in one click — it'll answer from your published articles. Import 1. Open your AI agent → Knowledge tab. 2. Choose Import from the Help Center. 3. Select the portal and the language. 4. Run the import: each published article becomes a knowledge document. Good to know - Only published articles are imported. - When you edit your articles, re-run the import: it refreshes the knowledge (without creating duplicates). - That's the strength of the system: the same content serves your customers in self-service AND your AI — you write it once.

👥 Conversations & Team

Reports: track your activity and your team

Reports show you your support activity and your team's performance. Go to the Reports menu (admins). The main reports - Overview (live): the account state in real time — open / unattended / unassigned conversations, agents online. - Conversations: volume, incoming/outgoing messages, first response time, reply time, resolution time, number of resolutions, bot resolutions. - Agents, Inboxes, Teams, Labels: the same metrics, but per agent, per inbox, per team or per label. - CSAT: customer satisfaction (see the dedicated article). - Bot: the volume handled by your AI agents. - Heatmaps: conversation volume by hour and by day. Date range and export Each report offers a date-range selector (last 7/30 days, 3/6 months, year, or custom), a grouping (day/week/month) and a downloadable CSV export. Good to know: the "Overview" is ideal day-to-day to see what's happening live; the "Conversations" and "Agents" reports are for steering over time.

👥 Conversations & Team

Custom roles: tailored permissions

Beyond the Administrator and Agent roles, you can create custom roles with precise permissions. Go to Settings → Custom Roles. Create a role 1. Name + description. 2. Tick the granted permissions: - Manage conversations, - Manage conversations you participate in, - Manage unassigned conversations, - Manage contacts, - Manage reports, - Manage the knowledge base. 3. Save. The role becomes assignable when inviting an agent. Good to know: custom roles are available on higher plans. Useful, for example, to give a manager access to reports without making them a full administrator.

👥 Conversations & Team

SLA: set response time targets

An SLA policy sets response and resolution time targets, to guarantee a service level. Create an SLA policy 1. Go to Settings → SLA → Add SLA policy. 2. Name + description. 3. Set the thresholds: first response time, next response time, resolution time (in minutes, hours or days). Leave blank what you don't want to track. 4. Option: apply only during business hours. Then apply the policy via the "Add SLA" automation action or from the conversation. Good to know: SLA is an advanced feature, available on higher plans. Conversations that breach a threshold are flagged.

How can we help?

Getting started

Channels (inboxes)

Integrations

AI Agents

Conversations & Team

Social media publishing

Billing & plans

Campaigns

Account & settings

Build your help center

Connect WhatsApp via Twilio

The AI action log: understand replies (and non-replies)

Import your help center into your AI agent

Reports: track your activity and your team

Custom roles: tailored permissions

SLA: set response time targets