Is Solve the right fit for your customers?

Your team receives repetitive one-touch type questions and systematically applies the same response over and over again. If your team could benefit from having these types of tickets removed from their queues, we can help!

How does Solve for Email work?

Forethought will identify common and repetitive customer questions associated with macros or knowledge articles from your team. We'll use artificial intelligence to learn from your past tickets and automate this process. Then, when a customer ticket comes in, Forethought will read, understand, and respond to it with the relevant macro. 

How does Solve Widget work?

The Solve Widget is an interactive, customizable widget that lives on your organization's webpage. It directs customers to their best solution and can surface the best-fitting article from your knowledge base to answer their issues or create a ticket for your team to answer. As the widget's owner, you will have access to editing this widget through the Forethought dashboard to continue improving the experience and the number of questions it deflects.

Unlike most Customer Support AIs, we use Natural Language Understanding (NLU), a cutting-edge AI technology, to train on your specific data. Our use of NLU means we are able to launch Solve in as little as 3 business days with above 90% accuracy. That, of course, is not the case for everyone. For more information, read some of our case studies here.

What kind of workflows can I use for Solve Widget?

Intents are essentially classifications for specific problem types. Solve tends to work best for repetitive support cases with rigid questions and answers.

Some examples:

• Password Reset / Login Assistance
• Pricing Inquiries / Quotes
• Delivery / Shipping

How many phrases are needed to train a Solve Widget Workflow?

An intent refers to the goal your customer has in mind when typing in a question or comment to the widget. Intents are how Forethought’s AI interprets what your customers are asking and determines the appropriate response to return, which deflects support tickets from being created and reduces your agent's workload. Solve Widget works best for frequently asked questions from customers that can be resolved with text responses that provide additional information or with a knowledge article.

You will need a minimum of 2 training phrases for each workflow! However, we recommend adding more than 2 to train the model on a wider variety of different ways a customer may ask a question and to differentiate intents.  

How much data do I need to have?

Our customers see immediate value when our Solve products have at least 1,000+ tickets per week. This is because there must be a sufficient historical usage of the macros you would like to Solve Email to use in response to your customers. Alternatively, if you do not use macros and prefer to send knowledge articles to your customers, having articles that address frequently asked questions is needed in order to allow Solve Email to send the appropriate article in its response to your customers. This allows us to ensure there is sufficient data to train and create a custom AI model that will accurately send the expected macro or knowledge article response back to your customers.

For Solve Widget, you don't need any data at all! However, utilizing a knowledge base to deflect questions or utilize our other integrations is the best way to get value from our product. 

What type of actions can it automate?

Within the Solve Widget, you can perform actions to pull, update, create, or delete information by using any valid and public API endpoints. You can customize these actions to automate and deflect inquiries from your agents. For more details, read about our widget action build feature here.

What platforms do you support?

We support various platforms, such as Zendesk, Freshdesk, Salesforce, Airtable, Intercom, and many more. For more information, see Available Connectors and their Requirements.

What languages does Solve Widget support?

For more information, see Supported Languages in Solve.

Is Assist right for your customer support team?

Assist uses AI to intelligently surface the best knowledge from every corner of your business to agents in real-time so they can answer tickets accurately and efficiently. 

How does Assist work?

Assist empowers your agents by bringing relevant knowledge articles, past cases, macros, and even personal notes right to the agent's help desk to meet SLAs and delight your customers. Learn more about how Assist helps customers stay efficient and organized.

What is Forethought Assist, and how does its Response Generation Feature work?

Forethought Assist is a Google Chrome extension that allows users to access all the features of Assist without making any changes to their help desk. It serves as a central knowledge hub where support agents can find the materials they need to resolve customer issues.

One of the most powerful features of Forethought Assist is its response generation tool, which helps agents handle tickets more efficiently. When an agent selects a ticket and activates the response generation feature through the Forethought Assist widget, the system automatically analyzes the ticket, historical tickets, and knowledge base articles to create a contextually relevant and customizable response that appears beneath the ticket summary. Agents can modify the response according to their preferences, such as asking it to "make it shorter," "more formal," or "more friendly," ensuring the reply is appropriately tailored to the customer's inquiry.

Will my agents be able to write their own documents in Assist?

Yes! Notes allow agents to supplement your organization's knowledge base with their own material. Additionally, Smart Notes (available only on the Assist Chrome extension) allows the creation of templates, the use of placeholder variables, and the sharing of notes and shortcuts.

Some example use cases include password reset, shipment status, product defect, or any response where agents respond in a common way to any customer request.

Teams can create collections of shared note templates, saving time by enabling them to pick from a library of pre-built notes that solve common issues or processes. Finally, agents can assign shortcuts to notes that instantly add them to ticket reply without having to search for the right note.

Which languages are supported by Assist?

The initial AI response will be drafted in the language used in the ticket. For example, if the ticket is in Spanish, the generated reply will also be in Spanish. Agents can regenerate any response to a desired language by typing "change to [language]" in the prompt feature. Assist supports the following languages: 

• Arabic
• Catalan
• Chinese (Simplified)
• Chinese (Traditional)
• Danish
• Dutch
• English
• English (Canada)
• French
• French (Canada)
• German
• Greek
• Hebrew
• Hindi
• Hungarian
• Icelandic
• Indonesian
• Italian
• Japanese
• Korean
• Malay
• Norwegian
• Polish
• Portuguese
• Portuguese (Brazil)
• Russian
• Spanish
• Spanish (Mexico)
• Swedish
• Tagalog (Filipino)
• Thai
• Turkish

Which ticket management platforms does Assist support?

Assist extension is compatible with the following ticket management platforms:

• Zendesk
• Zendesk Messaging
• Salesforce
• Freshdesk
• Kustomer
• ServiceNow
• Jira Service Manager
• Intercom

Can Assist retrieve content from other platforms?

Yes. Assist can retrieve content from the following platforms:

• Zendesk
• Salesforce
• Freshdesk
• Kustomer
• ServiceNow
• JIRA Service Manager
• Intercom
• Airtable
• Confluence
• Contentful
• Egain
• Elev.io
• Guru
• HelpJuice
• Jira (Cloud or On-Prem)
• Mindtouch/Nice CXOne
• Linear
• Odo
• Readme.io
• Snowflake
• Upland
• VanillaForums
• Wordpress

What is Discover?

Discover acts as your customers’ AI advisor, generating proactive insights, recommendations, and content. This includes automated knowledge base management, workflow optimization, and comprehensive support analytics.

Discover automatically extracts insights from your customer interactions, automatically identifies customer trends, recommends automation actions, and keeps your knowledge base up to date.

These insights can help you understand your customer pains, streamline your support operations, and cut down significantly on your support costs, all while improving customer happiness.

Why is it important?

Understanding customer interactions through customer queries that are unstructured and unpredictable is valuable yet could be time consuming. With Discover, we leverage NLU (Natural Language Understanding) to automatically and dynamically categorize tickets with performance metrics that are updated daily. This unlocks the use of customer interaction data to further bolster data-driven decision-making processes across your organization.

Key Benefits

• Optimize cost savings –Instantly surface recommended workflows, knowledge articles to build, and a case tagging taxonomy to help support teams save time, reduce costs and improve customer happiness. 
  

• Predict and prevent escalations –Leverage customer interaction data to identify new pains and get ahead of potential issues before they become critical.
  
• Collaborate on AI-driven insights –Visualize and share all of your data across departments to help teams proactively plan operations and identify improvement opportunities to streamline the support experience.

How can you leverage Discover?

• Maximize Deflection and CSAT with Optimized Workflows

  Identify bottlenecks in existing workflows and get AI-powered recommendations to maximize self-serve coverage.

• Automate Manual Processes with Knowledge Base Management

  Keep knowledge base up to date with proactive gap detection, and effortlessly create new articles using generative AI.

• Unlock Game-Changing Insights with Comprehensive Analytics

  Extract insights automatically, identify new support trends and topics, and automate actions with generative AI. Share customer support insights across departments to help teams proactively plan operations and identify improvement opportunities

• Optimize cost savings

  Instantly surface recommended workflows, knowledge articles to build, and a case tagging taxonomy to help support teams save time, reduce costs and improve customer happiness.

• Predict and prevent escalations

  Leverage customer interaction data to identify new pains and get ahead of potential issues before they become critical.

• Recommendations for improving self-service support
  Surface a series of topics to automate based on ticket volume and how fast it is to resolve. Discover will also include what the improved ROI is if automated.
• Content gaps and recommendations
  Identify and recommend relevant macros support agents can use in Assist to answer questions faster and provide customers with a more consistent experience
• Customer sentiment analysis
  Proactively identify customer sentiment and pains to get ahead of potential issues and improve CSAT
• Improved ticket routing
  Generate a case tagging taxonomy and update routing rules to ensure agents are working on the correct cases, whether it’s skill or product-based
• Discover emerging trends
  Understand and identify trending issues CX leaders might not be aware of so that they can take action before potential escalation or churn.
• Granular filtered insights
  Filter the automatically clustered tickets with associated ticket and agent data to get specific and granular insights.

What type of data can you classify?

Any type of incoming customer support ticket query in multiple languages can be classified.

What volume of tickets do I need?

At least 100,000 tickets historically to enable proper classification.

What customer support performance metrics are supported?

Performance metrics include:

• Volume
• First contact resolution rate
• Full resolution time
• Reply time
• First resolution time
• Number of customer support replies
• Customer sentiment during a ticket interaction

What is the difference between structured and unstructured data?

Structured data includes data that can be organized into a spreadsheet, like phone numbers, addresses, product names, and currency. This kind of data is easily analyzed and understood, but because it doesn't provide many details, it's quite limited in terms of how helpful and insightful it can be for teams. 

Unstructured data, on the other hand, makes up over 80% of support data. This includes emails, audio and video files, phone calls, and long-form articles. This type of data offers valuable insights and can provide customers with a gold mine of feedback for their teams. 

Which help desk is supported?

• Salesforce
• Zendesk
• Intercom
• ServiceNow
• Kustomer
• Freshdesk

For other help desks, contact your Customer Success Manager.

What languages are supported in Discover?

Discover supports 36 languages currently. Here is the list - arabic, bulgarian, bengali, catalan, central kurdish, czech, danish, german, greek, english, spanish, estonian, basque, persian, finnish, french, irish, galician, hindi, hungarian, armenian, indonesian, italian, japanese, korean, lithuanian, latvian, dutch, norwegian, portuguese, romanian, russian, swedish, thai, turkish and chinese.

Is Triage right for your customer support team?

Our AI routes tickets to the right agent so your team can focus on delighting customers instead of tedious manual work.

How does Triage work?

Unlike most Customer Support AIs, we use Natural Language Understanding (NLU), an advanced AI solution, to route tickets. Our use of NLU means we can launch your smart ticket routing more quickly and accurately. Want to learn more? Read one of our case studies here.

What can you predict on?

Any type of frequent incoming customer support query. For retailers and travel partners, that may be refunds, order status checks, or subscription changes. For our technology partners, it may be around quicker escalation, sentiment, SPAM filtering, or routing based on knowledge of local legislation.

What sort of accuracy do you see?

With end-to-end case resolution of common - and repetitive - ticket routing, we see upwards of 95% accuracy. For SPAM detection, the numbers can go up to 99.9%!

How quickly can you launch?

The model training takes as little as 24 hours! The entire implementation may take a week or two.

What volume of tickets do I need?

At least 1000+ tickets per week are the right scale to get the most out of Triage.

What platforms do you support?

Salesforce, Zendesk, Freshdesk, ServiceNow, and Kustomer - no matter the platform, we’ve got you covered.

What languages does Triage support?

We support almost any language you need. With NLU, Triage trains on your data so it can learn your language. 

Here is Forethought's list of currently supported integrations, including their required information, integration type, and type of data.