Free cookie consent management tool by TermsFeed Generative AI Skills [AI Capabilities]
Generative AI Skills
The capabilities described on this page are included in Appian's advanced and premium capability tiers. Usage limits may apply.


This topic describes AI skills that use generative AI to automate many common tasks in your business processes.

What is generative AI?

Generative AI models create new content. Generative models take a prompt as input (such as a question or request). As the model evaluates that request, it recalls what it knows about those characteristics. As it begins to formulate a response, it uses probability to determine what comes next.

The output is entirely new content. Rather than regurgitating information word-for-word, generative models can formulate more specific answers, crafted just for that prompt. Examples of generative models include chat bots and image generators.

When to use generative AI

Generative AI is very flexible, so you can use it in multiple ways in your Appian processes. You can use generative AI to summarize content, extract information you're interested in, and detect sensitive information. You can even specify how you want those results to appear: in code, a paragraph, or a bulleted list.

Here are a few examples of when to use generative AI in Appian:

If you want to… Use…
Quickly determine whether a form submission is a support request or a general inquiry Text classification or unstructured email classification
Extract essential details of a legal document, such as a contract Unstructured document extraction
Summarize action items and assignments in a meeting transcript Text extraction
Identify sensitive, legally protected information in a portfolio of medical documents PII extraction from documents
Evaluate if your business is a good fit for a contract opportunity Document summarization
Create content for a new product launch, in line with your business's branding Text generation

AI Skills using generative AI

All generative AI skills create a prompt builder AI skill with a pre-populated template based on your use case. You can adjust the prompt, control the temperature, provide examples, and test the prompt directly within the AI skill.

If you don't see an AI skill suited to your use case, you can always use the ai Prompt Builder. Use this skill to create a prompt to send to generative AI models. You'll tell the model what you want it to do using plain language. After adjusting a few settings and testing the prompt, you can see what the model returns based on your instructions. Use this skill to summarize long or complex text, generate new content, and more!


  • ai Text: Identify text based on certain traits. You'll tell us about the types of text you want to classify in your business process and provide samples of each type.


  • ai Text or Emails: Extract data from text or emails. You'll tell us what you want to extract and how you want that information to appear in the output.
  • Documents: Extract data from a document.
    • ai Unstructured: You'll tell us what you want to extract from an unstructured document and how you want that information to appear in the output. For example, this skill can help you extract data from large or free-flowing paragraphs of text, like contracts.


  • ai Text: Create text for any purpose. You'll tell us what text you want to generate and whether you want the output to include any specific logic, format, or other requirements.


  • ai Text, Email Text, or Document Text: Summarize text from any source, including emails and documents. You'll tell us what you want to summarize and how you want the summary to appear.

PII Detection

  • ai Text, Email Text, or Document Text: Extract personally identifiable information (PII) in a document, email, or text block. You'll tell us the personally identifiable information (PII) you want to extract, such as names or phone numbers.

Tip:  To use these AI skills in a process, add the Execute Generative AI Skill smart service to your process model.

What makes a good prompt?

In the context of AI, a prompt is how we communicate with the large language model (LLM) about what we want it to do. A well crafted prompt can help you communicate with the model more effectively, and reduce the amount of time you spend tweaking or troubleshooting.

Crafting a good prompt can improve:

  • precision and relevance of the model output,
  • efficiency by getting the desired response in one question,
  • safety by excluding undesired output, and
  • customization with our own relevant data.

If you're looking to build a prompt from scratch, you might want to consider the following aspects:

  • Define your use case: What do you want the model to do?
  • Tell the model what input to expect (defining the input data): If the prompt will always include content for a certain type or format, it may be helpful to tell the model this in the prompt. For example, "I want you to summarize this email text and provide a suggested response."
  • Tell the model what output you want (defining the output data): LLMs are not deterministic, so it is possible that the model won't always return data in the structure you specify. However, you can be specific about what you want the model to return. For example, you can tell the model you want the response to be in JSON, HTML, a bulleted list, or any other format. You can also tell the model to include its response between tags, to help keep the answer more focused.
  • Gather examples: You'll want to provide examples to help the model produce the answers you're looking for. Examples help provide the model with context, so it will produce output that's more specific to your request.
  • Consider length, tone, and audience: Another thing to consider when specifying the output is how it will be used and who will see it. Does it need to be a certain length, perhaps 3 paragraphs? Should it be written for a certain audience, such as customers? If you help define the context for the model, you'll get results that are more in-line with what you need.
  • Remember token limits: The model can process a set number of tokens, or units of analysis. The model will process your prompt and the input data. Keep this in mind when you craft the prompt, because the longer the prompt is, the smaller the input can be.

Tip:  Put the most important part of your prompt (such as output format or a specific question to answer) at the end of your prompt so the model is clear on what your ultimate request is.

Usage considerations

There are some requirements for the inputs for generative AI skills. Refer to the table below to see the requirements for each AI skill using that input type.

Requirement Document input Email input Text input
File type PDF, digital or scanned EML N/A
File size limit 25MB 25MB N/A
Page limit per file 100 pages N/A N/A
Open in Github Built: Fri, Jun 14, 2024 (05:47:37 PM)

Generative AI Skills