AI and Agentic Automation

Hello Appian Community, I am currently using AI Skills in Appian to extract data from a document. The extracted data is being saved as text at the process model level. However, I need to convert this text into JSON format for further processing. I attempted to use the a!fromJson() function to convert the text into JSON, but I am encountering an error during the conversion. Here is what I have tried: The extracted data is stored in a process variable of type Text (e.g., pv!extractedData). I tried using a script task to convert the text to JSON using: appian Copy code a!fromJson(pv!extractedData) However, this results in an error. Error Details: My Questions: How can I ensure the text data is valid JSON and successfully convert it? Are there specific considerations or configurations required when working with AI Skills and JSON data in process models? What are the best practices for handling such scenarios? Any guidance or examples would be greatly appreciated!

this error am getting how can i fix this am querying this data to display in grid, is their any other way to display the data ?

I Trained AI skills with 20 Documents(resumes) under both Highly Structured and Unstructured categories, for this accuracy rate for Highly Structured is 40% and for Unstructure it is 47%. Is there any other ways to extract document for my OCR activity

Hi I have to extract all user details into excel manually from one specific group it has nearly 6.5k users as the data is huge the data is truncated and cant copy all the user details and post to Excel below is the logic using to get users from group can you confirm is there any way we can get all this user details in batch wise like 1-900 later 901-1800 like that getdistinctusers(     topeople(       togroup(        123456       )     )   )

Hello everyone, Please have a look at below code:local!array1: { a!map(id: 1, name: "Name1"), a!map(id: 2, name: "Name2") }, local!array2: a!forEach( items: enumerate(10), expression: concat("key", tostring(fv!index)) ), here i want to extend array1 map key from array2, which is dynamically generated through array2 and values should be the value of id from array1. so i am expecting the new array would be like this: { a!map( id: 1, name: "Name1", key1: 1, key2: 1, key3: 1, key4: 1, key5: 1, key6: 1, key7: 1, key8: 1, key9: 1, key10: 1 ), a!map( id: 2, name: "Name2", key1: 2, key2: 2, key3: 2, key4: 2, key5: 2, key6: 2, key7: 2, key8: 2, key9: 2, key10: 2 ) } any easiest way to do this. Thanks in advance 

Hello, I need to create rule that takes an array of dictionaries in input and if multiple of these elements have the same "id" value, I want to take only the first one in a separate list: ri!list: { {output: "OK, id: "abcd", description: "hello"}, {output: "OK", id: "abcd", description: "hi"}, {output: "OK", id: "yxz", description: "bye"}, {output: "OK", id: "yxz", description:"goodnight"}, {output: "OK", id: "opt", description: "ok"} } the output should be the following: local!output:  { {output: "OK, id: "abcd", description: "hello"}, {output: "OK", id: "yxz", description: "bye"}, {output: "OK", id: "opt", description: "ok"} }

input: "Banana", output: "B---------------1" , "aaa---------------3", "nn---------------2"  any one try it anthor way .. { a!localVariables(local!data: "Banana",local!len: len(local!data),local!merge: union(a!forEach(items: enumerate(local!len) + 1,expression: local!data[fv!index]),a!forEach(items: enumerate(local!len) + 1,expression: local!data[fv!index])),local!all: a!forEach(items: enumerate(local!len) + 1,expression: local!data[fv!index]),a!forEach(items: local!merge,expression: index(local!data,wherecontains(fv!item, local!all),{}) & "---------------" & count(wherecontains(fv!item, local!all)))) }

Here, the integrationResponse.result.body is an array of dictionaries. However, the length function returns 1 if not using flatten. Not sure why this is happening. Please share comments/reasons if any.

How to ignore hypens while searching in the grid  In the above image, while searching in the grid after removing hypen also below data needs to be come..

Hi All, I am trying to fetch data details from an XML file which contains XML code of an Process Model.When I try to fetch the name , UUID or Pv's data using the following syntax for PV's : xpathdocument( docId , "processModelHaul/process_model_port/pm/pvs/pv[1]/name" ) for UUID : xpathdocument( docId , "processModelHaul/process_model_port/pm/meta/uuid" ) for Name : xpathdocument( docId , "processModelHaul/process_model_port/pm/meta/name/string-map/pair[1]/value" ) I am getting no response.when i checked in Community : https://docs.appian.com/suite/help/24.3/fnc_scripting_xpathdocument.htmlthere also it was mentioned the similar syntax that i am using.But still i am not getting why the I am getting null as output. Thanks in advance.

we have this grid but the user wants like below how can we transpose this grid to row wise grid

Hello, my team and I have used the new AI skill for an email classifier and we have several questions regarding the process.For some context, we need the AI to classify emails into three groups, lets say A, B and C. To train the AI we uploaded: for group A around 139 eml files, for group B around 103 eml files and around 70 for group C.Once it was "trained", it said it had an accuracy of 100% and it  concluded there were no errors in the training process nor the actual classifying process, but as seen in the picture, it seems the model was  only trained with few of the files we uploaded for each group.  We were a little surprised when we took a look at the metrics since 1- they were extremely successful and 2- the ai didn't use all the files we uploaded from each type. We still went ahead and tested it with new emails, 1 from group A, 2 from group B and another 2 from group C. The results showed all emails but one were classified as group A, and the

We have an expression rule that has not been modified since 2017. The developer who wrote the rule originally is no longer with the company. This rule is executing without error in our DEV, UAT, and PRODUCTION environments. However, when I go to the rule in Appian Designer, it's throwing an error, saying there is an undeclared local variable. Indeed, there is an undeclared local variable, and it is referenced multiple times in the rule. However, this rule is somehow working, otherwise we would see dozens of errors in Production on a daily basis (according to the rule's Performance Trends, it's hit several hundred times a day). How is this rule able to work correctly when it's called in Production, but becomes a problem when it's being modified in Appian Designer. It's worth noting that the rule is called by an Interface that (again) has not been updated since 2017, and still uses "load" and "with" instead of "a!localVariables" - and

Hi, I have a requirement where I need to find the count of how many times a keyword appears in a PDF. How can this be done?

Hi Everyone,  I recently created test cases for 100+ expression rules. When I tried deploying to higher environment, even though the deployment was successful - the test cases are not deployed for all expression rules. Only 2 expression rules got their test cases while others did not. Looking for some reason why this might happen?

How can we show output as given below in appian using expression rule? output: 1 22 333 4444 55555

this is the query how can i write a expression rule for this and the result will be like below

I am working a requirment where I need to show salary based on currency. In India, The currency is always displayed in lakhs and crores Ex: ₹10,00,000. I am using a!currency() function to acheive this. The function is returning the value in ₹1,000,000.00 format instead of ₹10,00,000. ...

Greetings I am trying to use Document Extraction AI Skill to save information in a Commission Statement. The Commission Statement has standard details (Statement Number, Statement Date, Total Commission Paid, Production Cycle etc. It then has a breakdown which has Commission Line Items (Client Name, Surname, Policy Number, Policy Type, Amount, VAT).  I have created a similar process model to the one in the Tutorial: https://docs.appian.com/suite/help/24.1/create-skill-doc-extraction.html I therefore have a Table that speaks to Commission Statements and a Table that speaks to Statement Items. No the problem here is that the Commission Statements record Type gets updated with relevant data from the Document, however the Statement Items information following the Reconcile Doc Extraction results does not populate into the Statement Items record type. I have created the One-To-Many relationship between the Commission Statement and Statement Items Record Type and left the Writ

I want to validate a website URL that goes as an input, requirement is to start with https://www. and with {.in, .com, .net}Please Assist, Thanks in Advance

Our user case is, We have an UI to manage the tasks where we have 2 dropdowns, Task Name and Precedent task name as shown below.Task Name -> Precedent Task NameTask A        -> ------Task B       -> Task ATask C       -> Task B Condition is,Task B can be dependent on Task A but Task A cannot be dependent on Task BTasks B & C can be dependent on Task A but Task A cannot be dependent on Task B or CTask B can be dependent on Task A and Task C can be dependent on Task B, but Task A cannot be dependent on Task C. Basically the requirement is to prevent creating circular logic among tasks. Since Task B is dependent on Task A, only if Task A is completed then Task B can be enabled. When user selects Task B or Task C as the precedent task for Task A, then a circular dependency will be created, hence to avoid this when user select B or C as Precedent task for Task A in UI, an error message should be shown. Today we have

Hi Everyone, Can anyone help on check box content extraction using appian AI. It seems like AI is not reading check box content. Do we need any specific configuration for reading check box content? Thanks in advance

How to write a rule which takes two input a char and an integer,ruleInput: (A,2)Output: (A1;A2)  anyone can give me the answer 

Hi Everyone, I have one requirement whenever any new request/case created auto refresh the Appian site tab. Example initial my site tab name as "Cases (10)" and whenever another case created from different source (Ex:Email), would like auto to refresh the tab name as "Cases (11)". I have tried with refresh variable, but it is not working. Can you please share any other workaround to achieve this functionality. Please let us know, If any queries. Thanks!!

Hi All, I have made my Appian Environment through appian community, but i am not able to see admin console and Appian cloud database. they are giving me the basic user permission not system Admin. earlier we are able to see Admin console and cloud database but for new version we are not able to see admin console. so how we can connect data source how we can see value in database if appian cloud database is not visible.