Meet Your AI Copilot for Customer Success
Vitally's native AI Copilot is available on Accounts, Organizations, Conversations, Meetings and Notes to help surface critical insights, ask the right questions at the right time, and take action faster from key customer interactions. AI Copilot includes AI Summaries, AI Actions, and Ask AI.
Instantly build rich, detailed customer profiles with AI Summaries for Accounts and Organizations
Ask natural-language questions to uncover next steps, churn risks, sentiment, and key insights across Accounts, Orgs, Conversations, Meetings and Notes
Make follow-up a breeze with intelligent AI emails, Task suggestions, and extracted Custom Objects from Meetings, Conversations and Notes
AI Actions
Choose from a set of automated actions to take from an Account/Org 360, Conversation, or Meeting to speed up follow-up and take action faster.
Depending on the object you're in, will depend on how you can gain access to it.
Customers (Organizations or Accounts) you can open up the Account or Org where you'll see a button on the top left called AI Copilot
If you're in a Meeting or Conversation, you'll see a tab on the top right
At the top of the Copilot panel, choose from a set of Quick Actions - these will change depending on what feature in Vitally you're using at the moment.
Available Quick Actions:
Quick Actions | What it does | Where it's available |
Create an Account/Org Summary | Generate a profile of any customer from a selected timeframe | Accounts/Orgs |
Suggest Follow-up Tasks | Populate a series of suggested Tasks related to a past engagement | Meetings, Conversations & Notes |
Extract Custom Objects | Pull out potential Custom Object items from an engagement to map to an existing Custom Object in your Vitally instance | Meetings, Conversations & Notes |
Draft a Follow Up | Write a follow-up Conversation to email the customer based on what happened in the Meeting | Meetings & Notes |
Suggest Follow-up Tasks
From any Conversation or Meeting, select the Quick Action to Suggest Follow-up Tasks.
Vitally AI will scan through your email thread or meeting transcript to extract relevant follow-up Tasks for you to complete.
Suggested Tasks will appear at the bottom of the dialog box. Hover over any Task and click the + icon to add it as a Task to this Account or the x icon to reject the suggestion. Vitally will automatically try to pre-select the project of the task based on context and participating accounts. If there is ambiguity or the AI is not 100% confident, it will fall back to the previous behavior, and you can manually select the project and milestone.
Extract Custom Objects
From any Conversation or Meeting, select the Quick Action to Extract Custom Objects.
Choose from the dropdown menu of the existing Custom Objects in your account (e.g., Product Requests, Bug Reports, Opportunities, etc.)
If your Custom Object already has a description, this will appear and you can edit it if necessary. If there is no description available, you will be prompted to add one.
Vitally AI will scan through your email thread or meeting transcript to extract relevant items to match your selected Custom Object.
Suggested Custom Object instances will appear at the bottom of the dialog box. Click each suggestion to accept it and have it automatically created. Or, hover over the suggestion and click the x to reject it.
Draft a Follow Up
From any Meeting, select the Quick Action to Draft a Follow Up.
Select whether you want AI Copilot to draft the follow-up from scratch or using a Conversation Template.
If you select "from a template," you'll be prompted to choose which Conversation Template you'd like AI Copilot to use.
Vitally AI will begin to draft a follow-up email, which will appear at the bottom of the dialog box. Click into the text box to open it as a Conversation draft.
From here, you can make any necessary edits and add personalization to the email. Make sure to confirm the correct sender and recipient details.
Once complete, send the Conversation.
Ask AI
One of the primary functions of the AI Copilot is to ask questions about your customers and your engagements with them to dig into risk, opportunity, sentiment, and beyond.
To Ask AI:
Open the AI Copilot on any Account, Org, Conversation, or Meeting.
At the bottom of the Copilot panel, choose from a set of pre-defined questions or type in your own freeform question into the dialog box at the bottom of the panel to get answers.
Depending on how much information is available and how recently Vitally AI was used on this Account, it may take anywhere from a few seconds up to a minute to load an answer.
Once you've received your answer, go back to the Copilot to ask more questions or use AI Actions.
Check out our FAQs below to learn how to best ask questions to Vitally AI!
FAQs
Who in Vitally has access to the AI Copilot?
All Vitally users have access to the AI Copilot in Account/Org 360s and Conversations. Users with the Gong integration or the Vitally AI Meeting Recorder enabled for their account also have access to the AI Copilot in Meetings.
Does Vitally use customer data to train AI models?
No. Customer data processed through Vitally AI is **not used to train AI models**. It is only used to generate the immediate output requested by the user (e.g., a summary, task, or note).
Is customer data retained or reused by underlying model providers?
No. Vitally uses **AWS Bedrock** as its AI infrastructure provider. Model providers (e.g., Anthropic, Cohere) do not have access to your prompts, data, or completions. Data is not made available to them for training or reuse.
What specific data is retained when using Vitally AI?
Inputs, outputs, and prompts are subject to Vitally’s existing **retention and deletion protocols**, the same as all other customer data within the platform.
How long is AI-processed data retained?
AI-processed data follows Vitally’s standard retention policies. No additional or extended storage is introduced by AI features.
Are AI-generated outputs (like summaries or tasks) stored?
Yes, AI-generated outputs (e.g., a summary, task, or note) are stored in Vitally if you choose to save them — just like any other object created in the platform. They are managed under the same retention and deletion policies.
Who are Vitally’s AI subprocessors?
Vitally’s AI features run on **AWS Bedrock**. AWS is the only subprocessor involved in handling AI-related requests.
Can you confirm that AWS Bedrock model providers cannot access my data?
Correct. AWS Bedrock uses a “Model Deployment Account” structure, meaning model providers do not have access to customer prompts, completions, or logs. They also cannot use your data for training or inference outside your request.
What types of questions can Vitally AI answer?
Vitally's AI model looks at past Meetings, Conversations, Notes, Docs, Custom Objects, NPS survey responses, and Custom Survey responses to gather information about a customer. The types of questions it can best answer are related to engagement with that customer that has been tracked in Vitally. Questions about the relationship you have with that customer, their sentiment about your product or service, and success planning are all supported. However, questions about items tracked outside Vitally (e.g. support tickets, product usage) or multi-part questions with dependencies are not supported.
Examples of ideal questions:
Have we heard complaints, negative feedback, or frustration from stakeholders?
Are there outstanding invoices or financial issues?
What does/doesn't the customer like about our product or service?
What are the customer's main product requests or gaps that they’d like to see filled?
What are the customer’s key goals or initiatives?
What does success look like for them in the next 3, 6, 12 months?
Examples of non-ideal questions:
Who are the new users and what does their engagement with us or the product look like?
This is a multi-part question with dependencies which is not supported currently.
Are issues being resolved promptly and to their satisfaction?
This question is not ideal since it is vague and subjective. A better question would be to ask about their customer's sentiment or satisfaction with your product.
How many support tickets have they submitted in the past 90 days?
How frequently are users logging in?
Has the customer experienced any market volatility or is there an recent relevant industry news?
All of these questions relate to information tracked outside of Vitally and not reflected in any of the supported Vitally Objects for AI analysis.
What kind of Conversation Template should I use for AI follow-ups?
Since the Conversation Template will form the foundation of the follow-up email that AI Copilot will create, it is recommended that you format these templates like a prompt rather than a traditional email template. By prompting the AI to pull out key details from the meeting, summarize them, and suggest action items, you will be able maintain your brand voice and consistency while leveraging AI to personalize every follow-up seamlessly.
Here is an example of a good AI follow-up Conversation Template:
Subject: Follow-up from [Meeting Name] with {Account Name}
Hi {Account Name},
Thanks for taking the time to meet today. Here’s a quick recap and next steps from our discussion:
Meeting Summary
Date & Time: [Meeting Date / Time]
Attendees: [List of Attendees]
Topics Discussed:
[Topic 1 Summary]
[Topic 2 Summary]
[Topic 3 Summary]
Key Takeaways
[Key Point 1]
[Key Point 2]
[Key Point 3]
Action Items
For {Account Name}:
[Action Item 1]
[Action Item 2]
For {First name sender}:
[Action Item 1]
[Action Item 2]
Next Steps:
[Brief description of what will be covered]
Thanks again, and please feel free to reach out with any questions before our next conversation. [Try to relate to the customer with a friendly joke with this paragraph].
What models does Vitally use?
At Vitally, we use Amazon Bedrock to bring powerful AI features to our platform. Bedrock gives us access to best-in-class large language models from trusted providers like Anthropic, Meta, Cohere, and others—without compromising on security or privacy. Not all models are created equal, and we use different models for different parts of our AI feature set. Most importantly, your data stays private. None of your information is used to train these models, and it never leaves our secure environment. Everything runs safely behind the scenes, so you get smart, reliable AI-driven tools—without giving up control of your data.
Is Vitally AI under the scope of our existing DPA and Privacy Terms?
Yes.
Does using Vitally AI require a separate customer opt-in under GDPR or other frameworks?
No. AI processing is considered part of Vitally’s **standard product functionality** under your existing DPA and privacy terms. No additional opt-in is required.