SAP Joule Is an AI Boost for BTP and Abap


I recently had the opportunity to attend a hands-on workshop on Business AI at SAP in Zurich. A team of developers from SAP Labs India flew in from Bangalore for the event, which the CTO of SAP Switzerland also attended. One of the special features of this event was the opportunity to receive input from top experts on site, to discuss it with them, and to try out the new possibilities right away.
AI setup via booster
The repertoire included ready-to-use services such as document information extraction, prompt engineering at the Generative AI Hub, creating an application in SAP Build Code with SAP Joule, SAP's own AI assistant, or using the SAP Hana Vector Engine to embed custom context for artificial intelligence.
What impressed us was how easy it was to use the services in our in-house BTP. They could be added simply to the BTP sub-account; they were easy to configure, and in many cases even with a booster, i.e. with guided setup. A completely new quality compared to the usual configuration of services on the NetWeaver stack.
Abap gets smarter and SAP Joule can manage Abap
But not only the services offered in BTP are interesting, AI is also finally finding its way into Abap development. With the Abap AI SDK, there is now a native option in Abap to integrate AI models directly into any Abap application—on S/4 Cloud Public Edition and S/4 Cloud Private Edition systems as well as in the BTP Abap environment. This enables the creation of new, innovative applications as well as the enhancement of existing implementations. Lastly, SAP Joule's capabilities have been extended—SAP's AI copilot can now also use Abap. Available as a new view in the Eclipse development environment, SAP Joule is available to programmers as an Abap sparring partner.
Abap code and CDS views can be generated, discussed, and explained using SAP Joule's chat feature. SAP Joule can also be used to automatically generate the time-consuming unit tests that programmers are less fond of. This not only saves time, but also increases the robustness of the code.
Promising roadmap
A look at the development roadmap shows that the next few months will also be exciting. SAP has planned major enhancements to the Abap functionality of SAP Joule. On the agenda is the complete generation of transactional applications (data model, behavior and user interface) and analytical queries.
This is where SAP Business AI comes into its own: it is the only AI that is trained with a focus on proprietary SAP data and the SAP architecture, and therefore truly "knows its way around" the SAP domain. Building on this foundation, SAP Joule can also act as a coordinator, optimally integrating AI agents, data, and processes.
All of these features offer incredible potential for development in the ABAP environment. Boring boilerplate code and test cases can be automatically generated in the future and developers can concentrate on the more interesting aspects of their projects. Even with Advanced Business Application Programming Language, aka General Report Processor. Thanks to Joule and co., Abap, which had already been declared dead, is now getting smarter.
To the partner entry:

1 comment
code quality guy
Zum Thema Joule und ABAP: Seien wir mal ehrlich: Ist denn die Testcode-Generierung wirklich das Problem gewesen bisher, warum Tests unbeliebt und selten waren? Oder ist es nicht viel mehr die Architektur eines SAP-Systems mit den ganzen historischen Altlasten und Quircks, die nie dafür gedacht und designt waren, automatisch testbar zu sein?
Wenn sich daran nichts ändert und Entwickler nicht umdenken und sich auf außerhalb der SAP Bubble längst etablierte Techniken wie bspw TDD und ernsthafte Softwarequalitätsstandards jenseits von naming conventions einlassen WOLLEN (anstatt halt in S4 so weiterzumachen wie sie es dir letzten zwanzig Jahre gewohnt waren nur mit Eclipse statt se80), wird mit historischem ABAP Coding trainierte AI auch nur das reproduzieren was schon in der Welt ist. Die Innovation und Wandel zu besserem und robusterem Code muss von Menschen ausgehen und sich in Trainingsdaten niederschlagen, bevor sie in generativer KI ankommt und das sehe ich ehrlich gesagt bei S/4 Projekten gerade nicht.
Also ich glaube, dass Boilerplate gut und schnell generiert werden kann – das allein ist ja schon ein Achievement. Aber wir werden auf absehbare Zeit keinen grundsätzlich besseren Code bekommen. Generative KI für Coding bedient sich für andere Sprachen an Open Source Projekten von denen die guten die Messlatte in puncto Coding Standards echt hochhängen und popliger Enterprise Code egal in welcher Sprache oder Plattform nie ranreicht. Wie will Joule also an gute Vorlagen kommen?