Appian Community and Appian Academy are being upgraded. From July 24–August 3, the Appian Community will be in read-only mode. During this time, the site will be read-only and user registration will be disabled. We apologize for any inconvenience this may cause, but a more secure, stable, and performant Community experience is coming soon!
The new Appian Community launches August 3, followed by Appian Academy on August 7. During the migration, Appian Community Edition, Appian Academy, Documentation, Certifications, Instructor-led Customer Training, Partner Sales Training & Accreditation, and Forum (for Appian Partners and Customers only) will remain available.
My use case is that I want to be classify documents into one of several categories, then depending on the category, extract certain fields from it. My question is for this kind of use case, what exactly is the difference between using AI Skills to do this versus using AI Doc Center? Looking around, I see some people saying AI Doc Center uses more tokens and that it can handle more complex cases, but I can't see anything in documentation about if that's actually true or not, and anything about when you'd want to use one or the other. I've been in loops reading the same page over and over again, so at this point I might have missed something, but if someone's able to help point me towards an answer, that would be most appreciated!
Discussion posts and replies are publicly visible
Hi kl0001 ,Adding to what others mentioned.
AI Skills are more machine learning (ML) based, where you typically train the model by providing sample documents for each category you want to classify or extract.
AI Document Center (Doc Center) is more Generative AI (GenAI) based, where the model can classify and extract information from documents using prompts and configuration, with less reliance on traditional model training. It also provides capabilities for monitoring, testing, versioning, and deployment of document-processing models.
AI Skills generally do not consume GenAI tokens when using traditional ML-based classification and extraction models.
AI Document Center is token-based for its GenAI-powered classification and extraction capabilities, so token consumption and associated costs should be considered when designing large-scale document processing solutions.
Do you know where I can find out how much running non gen ai skills would cost? Someone earlier said it counts as an AI Action, but when I ran a highly structured ai doc extraction skill, I did not see anything in perflogs/ai/ai_input_output_activity.log where I would usually see stuff like token costs and other ai actions
kl0001 You'll need to be on 26.6.105.0 or above, hotfix released on July 10th, and the relevant log file is artificial_intelligence.csv. If you're not seeing Actions there after upgrading, please open a case with Appian Support.
gotcha, does using more AI actions add on to some additional cost that someone maintaining the environment should be aware of?
Yes, customers have different allotments of AI Actions per month depending on their license tier and other agreements with Appian. Baseline info can be found here, but I recommend reaching out to your account team for additional details.
Thanks! Do you know what happens if an environment goes over the monthly limit? Is it a hard cutoff or an extra charge?
You're welcome! There is no hard cutoff at the platform level; rather, overages will be addressed by the account team.
The logs track both AI Actions and token usage, but It looks like based off the pricing documentation you sent, in terms of cost, we should be aware of AI Actions only since I do not see any pricing limitations around tokens. Is that true?