When to Use AI and ML

Appian provides a variety of low-code design objects, functions, and smart services you can use to easily integrate artificial intelligence (AI) and machine learning (ML) functionality into your application. This page highlights some common situations where AI and ML can be useful, and how you can use different Appian features to meet your needs.

• Already know what problem you're trying to solve? Learn when to use AI and ML.
• Looking for some inspiration? Jump to use case examples.

Appian's AI capabilities

Appian provides multiple ways to leverage the power of AI in your applications. Features marked with an asterisk (*) use generative AI.

Feature	Description	Uses Anthropic Models
Composer*	Use AI to plan and build applications by describing what you want in natural language and letting Composer generate a development plan and the application components to match.	Yes
AI Agents*	Build AI agents that can perform complex, multi-step tasks by combining multiple tools and integrating with your data fabric.	Yes
Appian MCP Server*	Connect external AI applications to Appian capabilities through Model Context Protocol (MCP), letting users interact with application data and business logic through natural language.	No
Advanced IDP Tools AI skill	Extract data from lengthy and complex documents with tables that span multiple pages, contain nested tables, or other complicated formatting.	No
Prompt builder AI skill*	Create a prompt to send to generative AI models.	Yes
Generative AI skills*	Generative AI skills provide pre-populated templates to help automate common tasks.	Yes
Document extraction AI skill	Use AI to extract data from documents.	No
Document classification AI skill	Use AI to identify a document's type based on certain traits.	No
Email classification AI skill	Use AI to classify emails based on content and context.	No
Sentiment analysis	Analyze text to determine its emotional sentiment.	No
DocCenter*	AI-powered document processing solution that combines advanced document extraction with generative AI capabilities.	Yes
AI Copilot for Reports*	AI Copilot helps business users gain insights from their data by generating reports and visualizations.	Yes
Process HQ*	AI-powered insights into your business processes, including suggested KPIs, views, ad hoc event detection, and insight summaries.	Yes
AI Copilot for Data Fabric*	Chat with your data fabric to explore and understand your enterprise data.	Yes
Documents Chat*	Chat with your documents to find information and get answers.	Yes
Records Chat*	Chat with your records to explore data and get AI-powered answers.	Yes
Enterprise Copilot*	AI-powered assistant that helps business users work with enterprise documents and data.	Yes
Smart Search	Semantic search powered by AI embeddings for more relevant search results.	No
a!callLanguageModel*	Call a language model directly from your Appian expressions to power chat interfaces, automate content generation, and process AI responses in workflows.	Yes
Chat field*	Add a conversational AI chat interface to your Appian applications so end users can interact with language models directly.	Yes
Process model recommendations	Get AI-powered recommendations for improving your process models.	No
Sample data generation*	Generate sample data for testing and development.	Yes
Test case generation*	Generate test cases for your Appian applications using AI.	Yes
Case Management Studio - Data Modeling Copilot*	AI-powered data modeling assistance in Case Management Studio.	Yes

Many Appian Solutions use these AI features to address specific use cases. The following tables describe which platform features are integrated into solutions and which AI provider each solution uses by default. Case Management Studio solutions and DocCenter use Anthropic models, while all other solutions use OpenAI models by default. Features marked with an asterisk (*) use generative AI.

Solutions using Anthropic models

Solution	Platform feature
DocCenter	Advanced IDP Tools AI skill, Generative AI skills*
CMS Module: Case Comments Summary	Prompt builder AI skill*, Generative AI skills*
CMS Module: Case Document Summary	Prompt builder AI skill*, Generative AI skills*
CMS Module: Case Record Chat	Records Chat*

Solutions using OpenAI models

Solution	Platform feature
GAM Source Selection: Document Chat	Smart Search*, Prompt builder AI skill*
GAM Source Selection: Evaluator Consensus Comment Consolidation	Prompt builder AI skill*
GAM Source Selection: Generate Consensus final comments	Prompt builder AI skill*
GAM Source Selection: Generate On Spot final comments	Prompt builder AI skill*
GAM Vendor Management: Opportunity Document Summarizations	Generative AI skills*
GAM Vendor Management: Document Chat	Smart Search*, Prompt builder AI skill*
GAM Vendor Management: Document Record Chat	Records Chat*
GAM Vendor Management: Message Summarization, Sentiment and Priority	Prompt builder AI skill*
GAM Contract Writing: Document Chat	Smart Search*, Prompt builder AI skill*
GAM Contract Writing: Contract Text Generation	Prompt builder AI skill*
GAM Contract Writing: Procurement Record Semantic Search	Smart Search*
GAM Contract Writing: Document Summarizer	Generative AI skills*
GAM Clause Automation: AI Clause Fill-in Identification	Prompt builder AI skill*
GAM Clause Automation: AI Rule Builder	Prompt builder AI skill*
GAM Clause Automation: Questionnaire Completion Assistant	Prompt builder AI skill*
ProcureSight: Semantic Record Data Search	Smart Search*
ProcureSight: Semantic Document Search	Smart Search*
ProcureSight: Search Result Match Reason	Prompt builder AI skill*
ProcureSight: Procurement Document Chat	Smart Search*, Prompt builder AI skill*
ProcureSight: Protest Analysis	Prompt builder AI skill*
ProcureSight: SOW/PWS Analysis	Prompt builder AI skill*
ProcureSight: Chat with Protests	Prompt builder AI skill*
ProcureSight: Chat with FAR	Smart Search*, Prompt builder AI skill*
ProcureSight: Market Research Agent	Smart Search*, Prompt builder AI skill*
GAM Requirements Management: Document Chat	Smart Search*, Prompt builder AI skill*
GAM Requirements Management: Document Summarization	Prompt builder AI skill*
GAM Requirements Management: Requirement Data Smart Search	Smart Search*
GAM Requirements Management: Generate RFI	Prompt builder AI skill*
GAM Requirements Management: Message Summarization	Prompt builder AI skill*
GAM Requirements Management: AI assisted requirement creation	Prompt builder AI skill*
AI Document Builder: Create template from reference doc	Prompt builder AI skill*
AI Document Builder: Answer Template Questions from Record Data, Notes or Documents	Prompt builder AI skill*
AI Document Builder: Generate document text from answers or user prompt	Prompt builder AI skill*
AI Document Builder: Edit Document Text from User Prompt	Prompt builder AI skill*

When to use AI and ML

I want to…	How Appian can help	Example use case
Generate a visual plan for my application development process.	Appian Composer in the Plan view	Application planning
Create and update design objects using natural language.	Appian Composer in the Build view	Build with Stories and Tasks
Build AI agents that perform complex, multi-step tasks.	AI agents	Automate complex, multi-step work
Enable users to ask questions about business-specific information, like human resources policies.	Enterprise Copilot	Document processing & procurement
Enable users to learn more about vast amounts of data.	AI Copilot for data fabric and reports	Customer support application
Quickly create realistic data to test my interfaces with.	Create sample data in record types.	Insurance claim application
Automate part of expression rule testing.	Create test cases for expression rules.	Insurance claim application
Create content as part of my business process.	Use a text generation AI skill to tell a generative AI model what text you want to generate and whether you want the output to include any specific logic, format, or other requirements.	Case management
Speed up interface development.	Build interfaces with AI	Insurance claim application
Quickly learn about data in your record types.	Chat with data fabric using the records chatbot component.	Case management
Build a chat interface with persistent conversation history.	Use the a!chatField() component with a language model to maintain context across sessions.	AI chat with persistent history
Call a language model directly in expressions.	Use a!callLanguageModel() to invoke language models and process AI responses programmatically.	Case management
Classify documents into categories specific to my business.	Use the document classification AI skill to build and configure AI models.	Insurance claim application
Extract data from PDFs without classification.	Use the document extraction AI skill to define your document structure for extraction.	Document processing & procurement
Manually confirm the results of data extracted from a document.	Use the Reconcile Doc Extraction smart service.	Supply management application
Classify text into categories from HTML or plain text sources.	Use the text classification AI skill.	Customer support application
Detect the language of text and translate it into the desired language.	Use the prompt builder AI skill.	Customer support application

Use case examples

Appian allows you to integrate modern AI capabilities like document classification, document extraction, and natural language processing seamlessly into your application.

Although you can leverage different AI services within minutes, it's important to consider practical AI adoption in your application.

Depending on the nature of your application, you could use AI to review files and extract key data points, gauge the happiness of your customer relationships, or collect and digitize handwritten information from contracts. Whatever your situation, it's best to consider how AI can improve or solve pain points in your existing process. Let's look at some industry examples.

Case management for large law firms

Generative AI

To help demonstrate how Appian can help your business be more productive using generative AI, let's look at an example in the legal industry.

A large law firm handles class action lawsuits and manages case data in Appian. A single case can include thousands of plaintiffs, so it could take a long time to look for the traits of interest that the plaintiffs have in common. For example, suppose a law clerk needs to determine how many plaintiffs reported a respiratory illness due to materials used to build apartments where they live. This could take a long time to research manually.

The records chatbot component can speed up this research tremendously. With this component, the law clerk can ask questions of record data, including related records, using natural language without needing to engineer a prompt. The component uses generative AI—powered by AI Copilot—to answer questions held within that record data. So if the law clerk asks the question in the context of the case record, AI Copilot looks within the related records (such as plaintiffs) to find the answers in a flash.

Where Records Chat surfaces information to help you make decisions, the text generation AI skill helps you complete the next steps. For example, you can use AI to produce communications in this scenario as well. Using the prompt builder AI skill, you can use plain language to ask an AI model to create whatever text content you need to complete your next task: summarize complex content for lay audiences, create email responses to common inquiries, and more.

When it comes to legal data, privacy and protection are two of the utmost concerns. The records chatbot component and prompt builder AI skill are entirely private AI, so you can rest assured that any inputs and outputs stay within your Appian Cloud site's boundaries and within your control.

Document extraction

The firm handles numerous non-disclosure agreements (NDAs) that require close review to ensure identified risks are mediated in the final agreements. The current manual review is time-consuming and prone to errors, diverting lawyers from higher-priority tasks. The Prompt Builder AI skill can automate this process by extracting and comparing relevant language from both original and negotiated documents. With the prompt builder, the law firm improves their accuracy, saves time, reduces risk of error, and allows their lawyers to focus on more strategic work, leading to an increase in process efficiency.

Document processing & procurement

Self-service knowledge

Imagine a state-level department that deals with procurement and contracts on a daily basis. Their workforce often has questions around the management of procurements. The department maintains a few key documents detailing procurement management, but each is long and dense with information. Today, many employees who have questions about procurements have to ask more experienced colleagues, or sort through multiple documents to get their answers. This process takes time for the curious employee, and for the individuals who are sharing their knowledge. This results in time away from other impactful tasks, as well as bottlenecks that prevent procurement from moving forward.

With Enterprise Copilot, the department can solve these challenges using a generative AI chat experience where users can ask questions about curated sets of information specific to their business. The department's knowledge set administrators can upload procurement documentation into a knowledge set. Appian AI Copilot then processes file contents and uses the information to provide deeper, more specific answers to users' questions. Whenever an employee asks a question, they'll also see which file was used to generate the answer, so they can continue learning about that part of the procurement process and trust the answer's accuracy.

Document extraction

Invoice and purchase order (PO) processing is essential for businesses across nearly all industries. As organizations scale, processing invoice and PO documents manually can quickly become a bottleneck for other workflows.

Let's say your Appian application supports a rapidly growing finance department. You have a limited number of employees, and they increasingly spend an overwhelming amount of time processing invoices and POs each day. Building a document extraction AI skill into your existing Appian workflows can take the burden off your employees, freeing them up for more meaningful tasks. Not only does AI take these tasks off your employees' plates, but AI performs these tasks far more quickly and accurately.

Invoice and purchase order document types are a great fit for automatic document extraction because they contain semi-structured data. This document type contains clearly labeled values that are easily extracted into key-value pairs.

Consumer banking forms processing

Document extraction

When working with sensitive financial documents at a bank, security is of the utmost importance. Yet, you most likely still process many forms manually on paper without a digital workflow. Because you often process thousands of these documents a week, these processes are error-prone and time consuming. You may already be using Appian to enhance your other workflows, so how can you take it one step further?

We recommend using built-in Appian document extraction to process your secure documents and keep all of your data within Appian Cloud.

Supply management application

Document classification + extraction

Now let's say you work for a company specialized in supply management. Every day, your Appian application receives several invoice forms that need to be audited and filed for processing. Since each form is structured in the same format and contains easily identified fields, you could delegate this task to Appian to extract the data from each field and then store the results.

Using AI skills and smart services, you can design your process to classify documents and extract data from them automatically and in the context of other steps of your process. If you want to confirm that the data extracted was correct before saving it to the database, you can build human-in-the-loop validation into the process to your employees are involved at the right place and right time.

A supply management application is just one example of using document extraction. You could apply this process to any type of application that requires a human to audit, review, or organize data from a document. Since document extraction focuses on fields, consider using these capabilities when processing forms like invoices, records, or applications.

Insurance claim application

Process models + document classification

Next, let's look at the insurance industry. Say your application receives hundreds of insurance claims a day, and your team is overwhelmed by the amount of claim data, which is slowing down the process and increasing the possibility for inaccurate decision making. With this example, AI can be used to improve the claim process.

To start, you can use Composer to quickly build a claims submission interface. Need to test the interface, but don't have data yet? You can also generate sample data to test the interface using realistic examples. If your interface uses expressions to dynamically populate content, you can also create test cases using AI.

Instead of having all claims go to one team to manually identify and sort through supporting documentation, you could delegate claims to different teams depending on where the damage occurred. Custom AI models can identify the types of documentation that accompanies each claim, so that the relevant teams are notified or involved at the right times.

Create an AI skill to use in the claims process. Within the AI skill object, define document types you expect to accompany incoming insurance claims. Use representative data sets to train the AI model to recognize each document type based on their unique characteristics. Then, configure the process model to follow different workflows based on the types of documents each incoming claim includes.

This is just one way the insurance industry could incorporate AI into their daily processes. Using Appian, applications like this one can easily benefit from full stack automation by leveraging low-code workflows, robotic process automation (RPA), and AI. Appian's Connected Claims Application demonstrates this by using built-in intelligent document management to evaluate claims and system-recommended investigation paths for intelligent fraud analysis. Paired with RPA, the Connected Claims Application allows you to pass data easily between different systems and view data in a unified interface within Appian.

Customer support application

Translation + natural language processing

Let's say your Appian application is built to manage a global customer support center. You receive support tickets from around the world in many different languages, and your support engineers need to be able to understand customer issues quickly in order to resolve them in a prompt manner.

To avoid slow resolution time and misinterpreting the customer's issue, you can incorporate AI translation into your application so each submitted issue is translated into the support engineer's native language. Using Appian, you can leverage the prompt builder AI skill to translate text and analyze sentiment in seconds. Add the skill to your process model and configure the smart service to use the text as an input. The text describing the customer issue is translated and appears in the support engineer's task in their native language.

Customer support related applications are prime candidates for numerous types of AI since they are responsible for constant and reliable communication with customers. Using AI, you can easily detect customer sentiment with natural language processing, properly understand a customer's issue through fast AI translation, or leverage document extraction capabilities to review and audit customer contracts.

Insights into case data

Depending on the size of your customer base, support cases may generate tons of data. This information is not only important to learning about how to improve your product or documentation to prevent future incidents, but also to help uncover insights on how to optimize the process and make it more efficient.

Suppose an analyst is tasked with learning more about how efficiently the support process solves customers' problems. Process HQ offers two ways to get these insights using AI Copilot.

The analyst is asked to build a report that shows the number of tickets in various statuses. He isn't sure which dataset contains the most relevant information for the report, so to start, the analyst can use AI Copilot for data fabric to ask questions about all of the available data sets. He can ask AI Copilot any of the following questions:

• What is the number of cases in each status?
• How many cases have been created by year and month?
• How many cases are assigned to each employee?

Because AI Copilot cites its sources, the analyst can also see the name of the dataset used to answer the question, as well as other details about the query. The analyst can then use the name of the dataset to start building the report.

After he selects the dataset and relevant fields, the analyst can begin to ask AI Copilot questions about the report. For example, he can ask "which factors help case workers close their cases faster?" and "What are some areas for improvement?". AI Copilot replies with insights in a fraction of the time it would take a human being to analyze the wealth of available data found in the report.

AI chat with persistent history

Suppose your customer support application needs a custom AI assistant that remembers previous conversations with each user. Support agents need to ask follow-up questions and reference earlier parts of the conversation without repeating context.

Using a!chatField() with a!callLanguageModel(), you can build a custom chat interface that maintains conversation history across sessions. The chat field component provides the interactive UI, while a!callLanguageModel() processes user messages and generates AI responses. By storing conversation history in a database, you can pick up where you left off, even after closing and reopening the application. See the recipe for building AI chat with persistent history for a complete implementation example.

Feedback