Getting Started with Thread
Onboarding Videos & Resources
Thread Training 1 - Getting Started with Thread
Thread Onboarding 2 - Thread Flows & Inbox Channels
Thread Training 3 - Thread AI
Messenger (Customer Chat Apps)
How-to Content for your Client End Users
Slack - Communicating with your customers about Thread Chat
Web - Communicating with your customers about Thread Chat
Windows Desktop - Communicating with your customers about Thread Chat
Microsoft Teams - Communicating with your customers about Thread Chat
CloudRadial - Communicating with your customers about Thread Chat
Getting Started with Thread's Customer Chat Apps
What are Thread's Customer Chat Apps? An Overview
Live Chat vs. Non-Live Chat - What's the difference?
Recommended plan for rolling-out chat
Step 1 of Setup: Customizing Messenger
Step 2 of Setup: Designing Custom Apps (Teams, Slack, Web, Cloudradial)
Deploying Messenger
Teams Service App
What is the Teams Service App for customers?
Design a custom Teams app for your customers
How to deploy the Teams Service App to a Customer
How to uninstall the Microsoft Teams Thread Service App
Slack Service App
How to test the Slack Service App in a Sandbox Environment
How to deploy the Slack Service App to a Customer
Desktop Service App
Web Service App
Messenger FAQ
Teams & Slack Companion Apps (for Service Teams)
Teams Companion App for Service Teams
Installing the Internal-facing Inbox Companion app for Teams
Troubleshooting "You don't have permission" error in Teams
Slack Companion App for Service Teams
Inbox
Inbox Channels & Flows
Getting Started with Inbox Channels & Flows
Use cases
Channels and Flows
Dynamic Flows - How to create a dynamic Triage Channel
What is Inbox and how do I use it?
How to track your time in Inbox
Sending attachments with Inbox
Save time answering chats with Snippets
Accessing & Installing Inbox
Can I style my messages?
Which shortcuts can I use in Inbox?
Setup an on-call member to be assigned
Members Management
Magic AI
Integrations
Autotask
How to setup the Autotask Ticketing Integration
How to enable Chat and Timepad insights in Autotask
Setting up an Email Communication Workflow in Autotask
Auvik
CloudRadial
ConnectWise Automate
How do I set up the Connectwise Automate Integration?
Deploy Messenger for Windows through Automate via Script
ConnectWise Manage
Thread Pods in ConnectWise Manage
How to enable Thread pods in ConnectWise PSA
How to setup the ConnectWise PSA Ticketing Integration
Adding permissions required to use Agreements/SLAs
IT Glue
Frequently asked questions
Security
AI Privacy & Security Overview
Data & Encryption
What if my organization has IP or domain restrictions?
List of Sub-Processors
Billing
How can I get help with setting up Thread?
Managing your Inbox notifications
How does Thread decide who gets assigned to dynamic Teams or Slack channels?
How to Setup a CSAT Survey
Can you add custom filters to Flows?
Can I get a custom Teams or Slack support app?
How do we request a feature that we need?
Is there a way to pull existing tickets to a channel in Inbox?
How do I upload a Teams app banner?
Can I disable the "New User" flow in Messenger chat?
I'm seeing tickets show up that were not created via Slack or Teams?
Internationalization Support
How can we send tickets from 2 or 3 service boards to Slack or Teams?
Which ticketing systems do you support?
Where can I find my Thread App ID?
Weekly Trainings & Office Hours
- All Categories
- Frequently asked questions
- Security
- AI Privacy & Security Overview
AI Privacy & Security Overview
Updated by Matt Linn
Artificial Intelligence (AI) Privacy & Security Overview
Thread Magic is the first AI assistant purpose-built for MSP technicians and service teams.
AI, Data Types & Security
We understand the importance of privacy and security—especially when it comes to early use of emerging technology such as large language models (LLM), generative artificial intelligence (AI) and generative interfaces. Any AI-enabled features from Thread will begin with the following foundational controls and principles.
It's also why Magic AI was built with an integration to Microsoft Azure OpenAI Service:
Our MSP partners benefit from the enterprise-grade and highly-secure Azure cloud.
1. No partner or customer data is stored in Azure, nor is it used for training or re-processing.
- No partner or customer data is stored in Microsoft Azure OpenAI Service.
- Data required for prompt execution (documented below) exists only in memory; it is not stored.
2. Data sent to Azure OpenAI Service for prompt execution is limited to the following:
- Contact First Name
- Contact Last Name
- Contact Type (as defined in the PSA)
- Date the Magic Action was called
- Issue-Specific Summary
- Issue-Specific Initial Description
- Issue-Specific Conversation Transcript
3. Access to Thread infrastructure and hosted services (AWS infrastructure, Azure OpenAI Service instance, Microsoft Azure portal, and underlying Microsoft services) is limited using the principle of least authority.
- Violations of Thread's internal Acceptable Use Policy will result in disciplinary action, up to and including termination.
Azure OpenAI Service & Thread Reference Architecture
When using Azure OpenAI Service, there are a number of security features built in to help protect your data and AI models.
Magic AI reference architecture.
These features include but are not limited to:
- Isolation: Thread’s Azure OpenAI Service instance is isolated from every other customer and partner on the platform, ensuring that there is no risk of unauthorized access to your data or models.
- Content Filtering: When data is submitted to the service, it is processed through Microsoft’s content filters as well as those built in to the specified OpenAI model. The content filtering models are run on both the prompt inputs as well as the generated completions. No prompts or completions are stored in the model during these operations, and prompts and completions are not used to train, retrain or improve the models.
- Control: Microsoft hosts the OpenAI models within the Azure infrastructure, and all customer data sent to Azure OpenAI Service is encrypted and remains within Azure OpenAI Service. Microsoft does not use customer data to train, retrain or improve the models in the Azure OpenAI Service, and neither does Thread.
- Data protection: Your data is not used to train or enrich the foundation AI model that is used by others. Nor is any data shared by Microsoft to OpenAI for improvement of their models. This means that you can be confident that your data is only being used for your own purposes and that you have complete control over how it is used.
- Compliance and security: The Azure OpenAI Service is protected by the most comprehensive enterprise compliance and security controls in the industry. This means that your data and AI models are protected at every step, from storage to processing to destruction.