Summary
Planhat includes AI Agents, and tools powered by Machine Learning (ML); plus, you can even integrate Planhat with your own LLM via your business license
Writing Assistant enables you to summarize text, generate action points, translate text, and more - you can even use your own prompts! Built-in next steps mean you can quickly take action, e.g. send the generated text via email
Conversation Summary summarizes a whole conversation, enabling you to quickly identify important points
Via Integrations, you can easily connect Planhat to your choice of LLM: OpenAI, Microsoft Azure OpenAI Service, or Google PaLM 2. Create Automations with your choices of prompt and actions - the possibilities are almost endless!
Planhat has built-in ML functionality to automatically detect spikes in time-series usage data, and determine which of your End Users are the most relevant
Who is this article for?
Anyone who would like an overview of AI functionality within Planhat
Article contents
Introduction
Planhat has always been at the forefront of understanding customers and prospects via data, and taking actions that are both informed by data and automated where appropriate. Artificial Intelligence (AI) is one way that Planhat helps you be more efficient and productive, by enabling you to complete tasks more quickly, gain greater insight into your customers/prospects, and make more informed decisions.
Planhat's data structure is highly compatible with Large Language Models (LLMs). With our AI functionality, you can blend public data that an LLM has been trained on, together with data from within Planhat.
The three main categories of Planhat AI features are:
Native Generative AI (Gen AI) tools, which work via Planhat's connection to OpenAI through Microsoft Azure. You consume AI credits in Planhat when you use these features
Writing Assistant - summarize text, extract action points, translate it, or even simply ask it to provide information. Then easily take action, e.g. send an email
Conversation Summary - summarize conversations (e.g. long email chains) so you can quickly see the key points without having to read through the whole thing
AI Integrations, which enable you to connect Planhat to your own choice of LLM (with your own license there) for Gen AI
Choose from Integrations to OpenAI, Microsoft Azure OpenAI Service, and Google PaLM 2
These connections can then be used in Automations, where you can define the prompt (which can blend external and Planhat data), and what action to take in Planhat when the answer is received
Machine Learning (ML) features, which are designed and implemented by Planhat and available freely within the app
Templated Calculated Metrics to identify deviations from normal, which you can use to automatically detect (and respond to) spikes in your time-series usage data
Relevance Score - a field on the End User model that displays how "relevant" that End User is, calculated automatically by Planhat via their activity level and interactions; you can then act (automatically or manually) in response to this data
In this article, we'll talk about each of these features in further detail.
🚀 You can alternatively watch an overview of Planhat's AI functionality in this video, which is also available in our in-app "how-to library".
1. Native AI features
Writing Assistant and Conversation Summary are built-in, native Generative AI features within Planhat.
What is Writing Assistant?
When you're writing notes (logging an activity, using the Conversation model) or writing in the description of the Issue model, you can highlight a piece of text, and select "Assistant".
You can choose from a variety of pre-configured prompts:
Improve Writing - rewrite a piece of text in a structured and more comprehensible way
Summarize - extract key details from a piece of text in a concise way, without losing important information
Translate - translate the text to the target language - currently supporting English, Spanish, French, German, Italian, Swedish, Portuguese, Russian, Polish, Chinese (Mandarin), Hindi, Arabic, Vietnamese, Korean, Indonesian and Filipino
Find Action Items - create a to-do list
... or even free-type into the Assistant if you'd like to use your own custom prompt, such as "write a follow-up email in Spanish".
🚀 Tip
As well as asking Writing Assistant to act on selected text, you can also simply ask it for information, similar to how you might search online. So, for instance, while you're writing notes during a customer call, if your customer mentions an unfamiliar term, you can look it up without leaving Planhat. It's more advanced than a simple search, though - for example, if you need to quickly generate a meeting agenda at the start of a call, Writing Assistant can come to your rescue and make this for you.
To do this, rather than selecting text you've already written, simply type a forward slash ("/") and select "Writing Assistant", and then enter your query.
Once the Writing Assistant has generated text for you, you can choose from a selection of pre-configured options to enable you quickly take action - for example, "Send Email", which opens a prepopulated window for you to review and confirm.
Why use Writing Assistant?
Writing Assistant is very flexible, so it has a wide range of use cases. For example:
If the meeting notes you write during a customer call are a big block of stream-of-consciousness text ...
you can use Writing Assistant to make them easier to read, for both yourself and colleagues
and quickly identify action items without having to spend ages reading through a confusing wall of text and manually writing a separate to-do list
saving you time, and making your work easier and less frustrating
If you have colleagues or customers around the world ...
you can easily translate your notes into another language, so your teammates can keep fully informed
and translate text for sharing with customers, such as via email, giving them the best possible experience
If you're in the middle of a meeting, and a customer mentions a technical or business term you're not familiar with
you can ask Writing Assistant to provide information on it
which gives you the knowledge you need quickly and easily - without having to leave Planhat
What is Conversation Summary?
Conversation Summary is a handy AI feature that lets you generate a quick summary of a long conversation thread (e.g. an email chain with lots of back-and-forth messages), meaning you don't have to spend time reading every single message all to understand the key points.
When you're viewing an applicable conversation, click on "Generate conversation summary" (the speech bubble icon), and Planhat's AI will read through the thread and summarize it for you.
If a conversation summary has already been generated for a conversation, you can click the same button to view it and see the date it was generated, and generate a new summary if there has been a lot of messages since then so you want an updated one.
Why use Conversation Summary?
Like Writing Assistant, Conversation Summary is a way that Planhat's native Gen AI features save you time by removing tedious manual work. It also reduces the risk that important information is missed because you didn't spot it buried within the correspondence.
Conversation Summary is particularly helpful if you weren't involved in a particular conversation - so you haven't seen the contents - but need to quickly know what's going on. For example:
You're a senior leader who's been brought in as an executive sponsor and you attend occasional meetings with a customer, perhaps because an issue has been escalated - you're busy and don't have time to read through a lengthy conversation thread, but you need to understand what's going on prior to a customer meeting
You're a CSM or TAM who's just been assigned an existing customer because the previous CSM or TAM has left your organization or is on vacation. You need to answer questions from the customer - perhaps on a call - but there is no time to review several very long email chains that have been ongoing with the customer recently
It can also be useful for your own conversations that occurred some time in the past - you can quickly and efficiently remind yourself of the contents using Conversation Summary.
Native AI features security considerations
These native AI features are powered by Planhat's connection to OpenAI through Microsoft Azure.
This means we (Planhat) have our own OpenAI instance through Azure, which lets us control data privacy and processing region. The input and output data is not available to third parties, and your data is not used to train the model. If you're in the EU, your data is sent to instances in EU (adhering to data regulations in the region), or if you're in the US, you will use the US instance. Azure does not store the requests or responses (with the exception that Azure checks the content of each request to check whether it is harmful, and if it is, then it's flagged and stored for 30 days; you can read more about this here).
When you use Writing Assistant or Conversation Summary, a request is sent from the Planhat API to our own instance of Microsoft Azure OpenAI, the request is processed, and the response is sent back to our API. Every step is encrypted through https. Whether the response is automatically saved or not depends on which feature you are using:
For Writing Assistant, the response is only shown to you, and is not saved to our database unless you choose to save it
For Conversation Summary, once we receive the response, we save it to the Planhat database to be able to show it again (when you want to view it at a later date) without reprocessing it
Native AI features commercial considerations
Because Writing Assistant and Conversation Summary use Planhat's Azure OpenAI connection, these features use AI credits within Planhat.
A request using Writing Assistant = 1 AI credit
Generating a Conversation Summary = 4 AI credits
Each organization (Planhat tenant) can access a free trial of these AI features. The free trial is 500 AI credits. This gives you the opportunity to try out the features and see how they help you.
When you have used your free trial, you can upgrade to a paid plan by contacting your CSM. There are different plans - with different numbers of AI credits per month - to suit your needs.
Whether you are on the free trial or a paid plan, the AI credits can be used by anyone in your organization (rather than belonging to a specific Planhat User). If you would like to restrict access to these features, you can do so via Role permissions.
2. AI Integrations
What are Planhat's AI Integrations?
Planhat's Operations Module includes a wide variety of Integrations to different tools, and this includes our AI Integrations. You can use the appropriate Integration to connect to your choice of OpenAI, Microsoft Azure OpenAI Service, or Google PaLM 2 - whichever account your organization is using.
A key difference between this and the native Planhat AI features of Writing Assistant and Conversation Summary is that the native tools use Planhat's connection to Azure OpenAI Service, but with these AI Integrations, you are connecting your own business AI license. You can think of this as "bring your own LLM".
You firstly connect up your chosen Integration using your credentials from the relevant AI provider; you can read more about this here. With these credentials, we can make API calls from Planhat to send prompts.
Then, you set up Automations using your AI connection.
You can create custom Automations, in which you have full flexibility in design
In some circumstances, you can use a templated Automation instead, which have some elements pre-configured for you for ease. In "upgraded Planhat" there are a variety of templated Automations related to AI for you to choose from. Speak to your CSM to learn more about upgraded Planhat
The general structure of each Automation will be:
The trigger - the change in data in Planhat (or schedule) that prompts the Automation to run
This is the same principle as any other Planhat Automation (i.e. not just AI)
E.g. when Company Phase is updated to "Churn Risk"
The prompt that Planhat sends to your AI provider / LLM (OpenAI, Azure or PaLM 2)
You can request information from outside of Planhat (publicly available information), but the prompt also can refer to data from within Planhat
E.g. ask it to summarize information about the Company whose data you send it, and write a tip for a CSM
The action(s) you want to happen when Planhat receives the response back
E.g. save it in a specific place in Planhat, and/or notify the CSM
We list more use case examples in the next section of this article, below, but the possibilities are almost endless! You have so much flexibility in how you use your AI connection in combination with Planhat.
Speak to your TAM or CSM if you need help with setting up Automations.
Why use Planhat's AI Integrations?
There are a wide variety of possible use cases when you're using a Planhat AI Integration in combination with Automations. Rather than having to choose from pre-set prompts and actions, you have free rein to prompt your LLM how you wish, potentially referring to both public data the LLM has been trained on, and your own Planhat data. You then bring your AI insights into Planhat, where all your customer data is compiled. This ability to blend external/public data and private Planhat data is highly powerful.
You firstly choose the trigger that causes each Automation to run. Here you define criteria, which could be a particular data change in Planhat (such as a Company moving into a specific filter), or a schedule (e.g. run every day at 5 am, or run once a week on a Monday at 4 am).
The middle stage of the Automation is where you write the prompt that will be sent to your AI provider. What text do you want it to generate for you? There are a vast variety of possibilities here! Below we list some example use cases that give you an indication of the types of prompts you could write.
Categorize NPS comments - prompt OpenAI etc. to assign a product feedback category (e.g. Product A or Product B, or bug report or feature request)
Company SWOT analysis (Strengths, Weaknesses, Opportunities, and Threats) - prompt OpenAI etc. to create a SWOT analysis for that Company
Company business health (gathering external data) - prompt OpenAI etc. to generate a score from 1 to 10, assessing the organization's performance, business reputation and industry viability
Key trends - prompt OpenAI etc. to list the key trends of the industry that that Company is in
Account summary - get data about a Company from Planhat, and then prompt OpenAI etc. to gather relevant external information and then summarize the data in a concise way - you can include really granular instructions in your prompt, saying what to include and what to exclude, and the structure/format of the summary (e.g. "Company Description", "Recommended CSM Actions", and so on)
Summarize recent Conversations - prompt OpenAI etc. to summarize the last X Conversation records of type Y
Sentiment analysis on chats or tickets - get data from a chat or ticket in Planhat and prompt OpenAI etc. to provide a sentiment analysis - e.g. this could be categorizing it into a pre-configured "bucket"
Churn risk response (triggered by e.g. a Company being assigned the "Churn Risk" phase) - send the relevant Company data to OpenAI etc. (which could be simply data on the Company model, or perhaps emails and notes on the Conversation model), and ask it to summarize the key data and write a tip for the CSM
Once your AI provider has generated the requested data and sent it to Planhat, the final part of your Automation defines what to do with that data. This is typically one or both of:
Save the information in Planhat in a specified place; for example, save it as a specific custom Conversation Type associated with the relevant Company
Notify the CSM (Account Owner) that the information is available, and they should take action. Planhat notifications can be in-app, Slack, email or desktop
Both of these options means that it's easy for you to take data-driven action, as well as visualize and analyze your data.
AI Integrations security considerations
Using your choice of AI Integration has the advantage that the AI account is yours - your choice of AI provider, and your connection. This means you have control over it, as opposed to using Planhat's connection to an AI provider. You can conduct your own internal security review, and choose the AI provider (LLM) that best meets your needs, and then connect your account to Planhat. If you have any questions about data location and AI training etc., those would be answered by your AI provider.
Once you set up the connection in a Planhat AI Integration, Planhat then has access to the AI provider, and can send your choice of prompts to it via its API. Your AI provider does not have access to Planhat data and can't request data from Planhat, although you can fetch any Planhat data within a Planhat Automation and then include it in a prompt to your AI provider.
AI Integrations commercial considerations
You use your own AI account (with OpenAI, Azure or Google) when you're using Planhat AI Integrations, which means there no additional cost on the Planhat side - the AI credits that are required for Planhat native AI features (Writing Assistant and Conversation Summary) do not apply here.
3. Machine Learning (ML) features
In addition to the native AI features Writing Assistant and Conversation Summary that work via Planhat's connection to Azure OpenAI, there is also built-in functionality within Planhat that makes use of ML, rather than connecting to an external LLM.
These are the "Deviations from Normal" Calculated Metric templates, and the "Relevance" End User system field.
What are "Deviations from Normal" Calculated Metrics?
Calculated Metrics enable you to build upon time-series data (such as the number of logins, or tickets, or reports downloaded, etc.), looking at averages and trends, and so on. Rather than needing your development team to carry out lots of different calculations for you, it's easy for you to perform these calculations yourself within Planhat. You can create custom Calculated Metrics, or use our Metric Template Library to apply pre-built Calculated Metrics.
In the Metric Template Library you will see a section for "Deviations from Normal", as shown below.
Clicking on one of the template options opens up a window where you can configure it, so even though it's pre-built, you can still tailor it to suit your specific needs.
Why use "Deviations from Normal" Calculated Metrics?
These Calculated Metrics help you to identify when time-series data is very different from its historic trending average, so they are great for detecting deviations and anomalies.
In other words, they keep track of your data and flag anything that's out of the ordinary.
As with other Calculated Metrics, you can then act in response, either manually or automatically - for example, a Workflow or Automation could be triggered when there are positive or negative signals, so you don't miss opportunities or risks.
What is the Relevance Score?
"Relevance Score" is a system (default) field on the End User model that shows you, at a glance, how "relevant" that End User is.
To calculate this, Planhat uses a special algorithm to assess each of your End Users and compare them to the others within your Planhat tenant. The Relevance Score is calculated automatically via their activity level (usage) and interactions (with your team, as detected via emails, tickets and meeting notes etc.), and it considers both recent data and data over time.
Each End User is given a score from 0 to 100, and this is categorized into High, Medium and Low. The field displays these color-coded values, but if you mouse over this you will see that End User's precise score out of 100 in a tooltip, as illustrated in the screenshot below.
Why use the Relevance Score?
This is a really quick and easy way to help you target your actions to make the most impact. High relevancy End Users may be suitable for advocacy programs, whereas low relevancy End Users may need support to get them engaged.
As usual in Planhat, this data can be used in numerous ways for analysis and data-driven action. For example, you could trigger a Workflow or Automation for End Users with a Relevance Score higher than 80 - maybe you want to automatically email them to ask for a review, for instance.
ML features security and commercial considerations
Both "Deviations from Normal" Calculated Metrics and the Relevancy Score field use intelligence built into Planhat. They do not connect to any external LLM, so there are no additional security considerations or pricing implications.
Next steps
🚀 Tip
An "AI Insights" Page (dashboard) is a great way to display data from the various AI tools within Planhat. Check out the example below for inspiration!
Click the image to view it enlarged
If you'd like to learn more about topics mentioned in this article, you can check out these articles: