AI and Rules - Recent Threads

LLM execution failed: EVENT_NOT_FOUND - No event exists with name: setVariableValue

pradeepkumawat — Wed, 20 May 2026 08:26:03 GMT

I am facing error in the AI agend while reading the document.
LLM execution failed: EVENT_NOT_FOUND - No event exists with name: setVariableValue
Steps1: When I am passing this document as in the TOOL in the AI agend than it is working fine.
Steps2: When passing this document in the input than facing this issue.

Please just How can I pass document dynamically in the process model?

AI Document Extraction

Kavya — Sat, 16 May 2026 06:33:20 GMT

Hi Everyone,

We have a requirement where we are using AI-based document extraction to extract fields from a predefined form.

In the same form, if there are any empty spaces and the user accidentally adds handwritten text or notes outside the expected form fields, we need to detect that additional handwritten content separately.

Is it possible in Appian with help of AI extraction to achieve this use case ?

Kind Regards,

Kavya

Smart Search Indexing Failure

jamesm4933 — Thu, 30 Apr 2026 16:20:13 GMT

I have a Record Type with a Document record field. We have a business requirement to be able to use Smart/Semantic search on this and a text field.

The Smart Search Sync consistently fails with the following error message, and a list of failed record ids: "Cannot retrieve the document. Verify the document management record type is configured correctly."

Through investigation, we discovered, that the Document field for these records was NULL, which is consistent with the above error message.

We would like to have a successful search indexing, for this record type, and so we removed those records from the dataset temporarily. However, now we get the following error message: "We couldn't check the smart search status. Try resyncing your record type."

Attempting to Sync is what produced this error, so it seems a bit unhelpful as an error message.

Why is the indexing failing when the selected smart search field is empty? Is there a workaround?

Now that the Smart Search syncing is failing with no further information, what can we do?

I am using a!currency to show thousand separator

shridevim9458 — Fri, 17 Apr 2026 10:12:45 GMT

I am using a!currency to show thousand separator but it by default shows $ symbol if used USD ISO.Here I need to remove this $ symbol while displaying this field.

AI Agent: INVALID_TOOL_RESPONSE

David G. — Wed, 15 Apr 2026 19:19:59 GMT

Sometimes, when I test an agent, it processes for a while, then after a few minutes throws this error:

System Error

This appears to be a system issue. Try again later or submit a support case if the problem continues.

Source: Run Agent - Agent: DG_testAgent - Run ID: 52

Details: LLM execution failed: INVALID_TOOL_RESPONSE - Required schema field not provided in data tree: textValue

Any suggestions on what could be going on? Sometimes the agent succeeds, but the frequency of getting this error makes me concerned about using this in production.

26.3 environment hosted on Appian Cloud.

"read msg" smart service with .msg to html confusing to AI in some instances

ericc087568 — Fri, 10 Apr 2026 21:36:22 GMT

I have a subset of .msg files which when read with the read msg smart service, render in a tiny font with the .html output which results in AI being unable to interpret.

Would I probably be better off running several reg ex statements to exclude tags that are confusing it and pasting in some style that would force the font, or just use the extracted (not the generated result document), or move it to PDF, or some different approach?

Regards,

Eric Casteel

AI Doc Center

shivakanthreddyp0001 — Tue, 07 Apr 2026 00:05:48 GMT

Hi All,

We were previously using AI Document Center 2.9, and whenever we created a classification model, the system would automatically create the corresponding classification AI skills in the Generated Objects application.

Recently, we upgraded to Document Center 3.1. After the upgrade, when we create a classification model, the AI skill is no longer created automatically.

Upon reviewing the Create Classification process model, I noticed that it was updated as part of the upgrade and no longer calls the “create objects” process model, which the earlier version did.

Is this the expected behavior in Doc Center 3.1?
Or is there any additional configuration or post‑upgrade step that we might have missed to enable automatic AI skill creation?

Thanks in advance

AI Skill Doc Extraction

leelaraok0002 — Fri, 27 Mar 2026 16:24:58 GMT

can we configure human task where api kicks appian process which ahs doc extraction ai skill in case doc extraction fails

What is a best practice for checking extraction instance result in AI Doc Center for further routing to custom reconcile?

ericc087568 — Thu, 26 Mar 2026 22:06:39 GMT

First of all, AI Doc Center is fantastic (3.1.3 installed). Love the way it is easy to set up and version classification and extraction, so much right out of the box.

I think I'm missing something in the documentation though on AIA Extraction Instance's status in a 'real' extraction. I see some constants in the AIA app and can infer in a different app that a status of 2 or 4 means a particular thing that might send me to my custom interface for reconciliation of the instance, which in turn would trigger a model to save to data fabric if reconciled and not abandoned / canceled by an end user. But, I'm getting off track...

I guess I'm asking what is the best practice to see the AIA Extraction Instance's notion that accuracy / precision / validation rule fail on an extraction would drive the decision to send a custom user reconcile task. At the moment, I would be cobbling together a big 'Or' to see if any reconciliation should be routed.

Regards, and see anyone at Appian World 2026?

Comparing two documents and return the matching Score(Signature Matching)

keerthirak779572 — Wed, 25 Mar 2026 10:25:42 GMT

I am having two Signature Documents. i want to compare both the documents and i have to return the matching score percentage of how similar two of the signatures.

AI Document Center Classification Model - "Unsupported file type" when uploading .eml file

Georgios Pavlidis — Tue, 17 Mar 2026 09:57:26 GMT

Hi everyone,

I am working with AI Document Center in Appian and I am trying to use a classification model with an .eml file.

According to the documentation, .eml should be a supported file type, but when I run the model I get this error:

Generative AI
Classification: Unsupported file type. Try again using a supported type or contact your admin if the problem persists.

The issue happens specifically when I upload an .eml file

Has anyone successfully used .eml files with AI Document Center classification?

Smart Search, Documents and RAG

jamesm4933 — Thu, 12 Mar 2026 15:16:52 GMT

My client is concerned about reducing token usage, and we are investigating how to prevent repeated tokenization and embedding.

We understand that Document Management Record Types embed the document representations for use in the smart search. Are these embeddings used system wide when document content is provided to an AI Agent or Skill?

Are they only available if the document is referenced using the special system document type?

Help us understand.

Thanks!

Composer

rohity0003 — Wed, 04 Mar 2026 15:42:34 GMT

Hello, we are starting the use of composer, and could use some light on this:

When an application is started with composer and it's objects created, how do we know what objects need to be completed or created?

How to check if a record is empty? (No keys)

deepakrana77 — Tue, 24 Feb 2026 08:26:29 GMT

Hi everyone, do we have any workaround to check for an Appian record which is null(does not have any key)? One way is check for a!keys and then check if empty, any other way?

So basically we had a use where there are multiple grid but they being sourced from the same record, let's suppose it be a room. So parent interface has parent room record variable and in child interface(contained each grid based on room type) we are sending parent by indexing the types. For deletion case, we are saving "null" in the same variable if it is new and if something already exist in db then update the isActive flag to false. Before saving the parent room record(which has all type of rooms) we were doing a reject to remove all the nulls. This used to work before and the "null" which we saved was still a null but now it is becoming a record type of null. Not sure if Appian fixed something on this behavior from there end or not.

documents Chat Field

rajeshp7374 — Wed, 18 Feb 2026 09:50:33 GMT

Hi Team,

I am working with the documentsChatField in Appian. After uploading a document, I want to pass it to the chat field for verification. If the verification is successful, I need to save the document details in the database.

Could you please guide me on how to achieve this? Is it possible to trigger document verification immediately after upload and then conditionally persist the document metadata based on the verification result?

Process Generation Not Working - Appian Composer

Himanshu — Mon, 16 Feb 2026 11:31:28 GMT

I'm having trouble generating process objects in the "Compose your application plan" screen.

When I click "Generate Process" in the Process tab, it shows loading but then nothing happens - the tab remains completely empty and no process is generated.

And because process tab is empty I'm unable to generate objects from composer

Has anyone encountered this before? What could be causing this issue?

Appian Version: 25.4

Doc Center Optional value

Sai Deepan Ramesh — Wed, 11 Feb 2026 23:24:45 GMT

Hi everyone,

If the AI extracts a value from a document that does not match any of the values provided by my Option rule (Expression Rule), what is the expected system behaviour?

The Setup:

Options Rule: An expression rule returning {"Access", "Avenue", "Beach", "Court"}.
Extraction: The AI correctly extracted the value "Access".
The Problem: Even though "Access" is in my list, the instance status is "Extracted with Errors".
The Error Message: "The following contain invalid values: streetType"

My Question:
If the extracted value matches the Options rule exactly, shouldn't the status be "Extracted" (Success)? Why is it flagging a match as an invalid value? There is no issue with extra space or formatting issue.

KeyWord Match in Document Extraction

ghanashyam905071 — Tue, 10 Feb 2026 03:58:16 GMT

Hi ,

I am using Appian Doccentre to look for few of the keyword to set one of the variable value. In my model I have created a field and given description/prompt to look for few of the keyword and if those found, then setting that new field value to those keywords in a comma separated way. The issue is, I am able to find few of the keywords but unable to find some although those are there in the document. I have tried giving all possible prompt but still unable to get those keywords. Did anyone find any such issue ? Any help is really appreciated.

I am giving my prompt something like this..

From ONLY this list: ["abc","def","pqr"], return a comma-separated list of those found anywhere (case-insensitive). Match whole words; treat “claims” as “claims”. Include headers, footers, labels, and stamps.

Regards,

Ghanashyam

Providing Dev Environment access to AI like ChatGpt or Claude

pratosh — Sat, 07 Feb 2026 17:09:49 GMT

How can I give the entire Dev access to a AI agent like how we provide access in VScode, Github so that the AI can have the full context of the applications and can reply with accurate results.

Try Prompt builder

Prakash — Thu, 05 Feb 2026 12:03:57 GMT

In Community edition , I am not able to find "Try Prompt Builder" under AI Skills . Do I need any other permissions for that ?

Semantic Search Tool Error AI Agent Studio

Vasil Chetinov — Wed, 28 Jan 2026 14:00:49 GMT

Hi I'm experimenting with the AI Agent Studio object and setup a test case to read excel file, but when it tries to use the Semantic Search Tool I always receive this response.

An error occurred while executing the tool [SemanticSearch]: The user [username] does not have sufficient privileges to perform the requested action.

And return error from the tool. Is there anything that need to be setup or allowed?

AI Doc Center: sourceDocumentId equals documentId causing reconciliation failures after document deletion

SHKEXL288968 — Tue, 27 Jan 2026 06:18:26 GMT

Hi all,

I’m using AI Document Center (AIDC) extraction models in a process to save extracted data to the database, and I’ve run into an inconsistent behavior between two models.

Scenario

1. 1. A user uploads a document into my application.
  2. I save that document into an application folder.
  3. I send the document to an AIDC extraction model.
  4. After extraction, I delete the uploaded document from my application (using standard document deletion so it’s removed from Appian).

Observed behavior

For Extraction Model A, the Extraction Instance record has:

sourceDocumentId = 46852
documentId = 46856

I delete the document my app knows about (46852). I can still open the Extraction Instance and reconcile without errors, which suggests AIDC is using documentId (46856), not sourceDocumentId.

For Extraction Model B, the Extraction Instance record has:

sourceDocumentId = 46908
documentId = 46908 (same value)

When I delete the document from my application (46908), I can no longer open the Extraction Instance. I get an expression error indicating the document is not available or has been deleted. This matches the general behavior that if a referenced document is deleted, any process or interface that tries to load it will fail.

Questions

What is the intended meaning and usage of sourceDocumentId vs documentId on the AIA Extraction Instance record?
Under what conditions would sourceDocumentId and documentId be different (Model A) vs the same (Model B)?
Is there any supported way to ensure that the document used by AIDC for reconciliation is a different document ID than the one my application deletes (like in Model A), so that deleting my “application copy” doesn’t break reconciliation?
Is the equality of sourceDocumentId and documentId for Model B expected behavior, a configuration issue, or a bug?
Given that the public docs don’t describe these fields, what is the recommended pattern for:
- Safely deleting or cleaning up documents used in extraction, and
- Avoiding reconciliation failures when documents are removed from the application?

AI Agent returns empty result for Excel file

adamb9906 — Tue, 27 Jan 2026 00:24:28 GMT

I’m testing an Appian AI Agent that needs to read data from an XLSX document. I have two copies of the exact same XLSX file stored in two different folders in Appian.

When I point the AI Agent to the file in Folder A, it works as expected and can read/extract the data.
When I point it to the identical file in Folder B, it does not work (the agent appears to find nothing in the file / doesn’t extract data).

Both documents are valid Appian documents of type .xlsx, AI Agent uses Semantic Search to read the data, and the file contents are identical. The only difference is the folder they’re stored in.

Has anyone seen this behavior before or can suggest what to check? Any guidance on why the same file would work in one folder but not another would be appreciated.

I created new folders, checked the folder security, but I can't find the issue.

AI Doc extraction returning a dictionary instead of text. Error displayed on the extraction summary page

Anu R — Mon, 26 Jan 2026 06:57:29 GMT

Hi all,

I am using the AI Doc center version 2.9. I am trying to extract invoices with single and multiple line items. There is a field called service code, which needs to be a list of string. In the extraction details, I have given an options rule, which returns a list of string values, based on the type of invoice.

The prompt for this field is: " This should be selected from the values in the options. This value should be null if it is a dental receipt. Please ensure you return a text value. When it is a single value, please ensure you return a single text value."

The extraction is working fine when there are multiple line items in the receipt. If it is a single line item, the value is extracted as {"[value:Chiro-Init", "spanId:99492f14]"}. I need the value to be "Chiro-Init".

Due to this, the extraction summary page is displaying the error: "A rich text item or rich text list item in a rich text display component [label=""] has an invalid value for "text". Text can only be of type date, date and time, decimal, rich text icon, integer, rich text item, text, time, or user. Received Dictionary."

Since the summary page is not displayed, I cannot even reconcile to select the right value for this field.

Please help me if you have a solution for this.

Thanks & Regards

Anu

How will confidence score improve for a field in document extraction in docCenter?

himanshut0007 — Fri, 23 Jan 2026 07:44:36 GMT

If I run extraction again and again for same document, still confidence score is same for that field. If confidence score is greater than threshold, want to skip reconciliation and map the details. How will confidence score improve for a field in document extraction in docCenter?