Skip to main content

    Filter by idea status

    Filter by product

    1123 Ideas

    Python Script Actions Support in Agent Studio6. Delivered

    Introducing Python Script Actions — now Generally Available in Agent Studio across all commercial regions! Building custom logic in your agents just got a massive upgrade. One of the most consistent requests from developers has been clear: "APIthon is too limited — I need real Python with real libraries." Until now, you were stuck with a restricted scripting subset, making complex data transformations, calculations, and text processing either impossible or painfully hacky.Python Script Actions fix that.You can now write full Python 3 code directly inside Agent Studio (screenshots of old and new experience attached) — with access to all built-in modules and a curated set of pre-approved external libraries. Python Script Actions plug into Compound Actions and Conversational Processes exactly like APIthon scripts do, but with dramatically more power. Define input arguments from slots or previous step outputs, write your logic, and the value of the last line of code becomes your output. That's it!What's included:Full Python 3 with all standard libraries (json, datetime, re, math, collections, etc.) 8 pre-approved external libraries out of the box:  pandas , numpy , scikit-learn , beautifulsoup4 , nltk,  plotly ,  seaborn , pycryptodomex Same integration model as APIthon — define input args, write code, last line = output Built-in testing in the Agent Studio editor before you deploy 6 supported data types for input arguments: string, integer, number, boolean, array, objectFull documentation: Python Script Actions ReferenceTry it out and let us know what you think!  

    priya.kornalius
    priya.kornaliusKnown Participant

    Interception is not passing the recommended KB links in ticket comment1. New

    We're experiencing several interception issues with the Copilot version of the bot, which has made the experience increasingly frustrating for the team. I’m documenting one such issue below for the product team to evaluate as a potential improvement opportunity.In the classic version, when the bot intercepted a ticket, it posted its full response along with the referenced KB article links directly in the ticket comments. This was extremely helpful, as it allowed us to:See which KBs were recommended to the user Track the bot’s response accuracy Take corrective actions by updating or improving the KBs based on user feedbackHowever, in the Copilot version, the bot only adds the answer summary in the ticket comment without any reference to the underlying KB sources. Since the bot is summarizing content from the top-ranked results, we have no visibility into which KBs were used to generate the response. This lack of transparency makes it difficult to validate or improve content quality.Moreover, we can’t depend on end users to manually share this information from their chat platforms each time—it’s neither scalable nor reliable.We’ve lost many of the valuable capabilities that the classic bot used to support, and this is affecting our ability to govern and improve content effectively.SuggestionInclude the source KB links or identifiers along with the bot’s response in the ticket comments, just as it worked in the classic version. This will improve traceability, content governance, and user trust in the system.