German Federal Employment Agency automates Jira ticket creation with an on-premises multi-agent AI system built with Capgemini
The Bundesagentur für Arbeit and Capgemini built a multi-agent system (reader, planner, creator and reviewer agents with human approval) that turns Requests for Change and user stories into Jira tickets. It runs entirely on-premises in the agency's local Jira instance, orchestrating Aleph Alpha, LLaMA and Mistral models via CrewAI, with all data remaining inside the agency's infrastructure. The source reports a significant reduction in manual effort and promising pilot results, without figures.
Overview
The Bundesagentur für Arbeit and Capgemini built a multi-agent system (reader, planner, creator and reviewer agents with human approval) that turns Requests for Change and user stories into Jira tickets. It runs entirely on-premises in the agency's local Jira instance, orchestrating Aleph Alpha, LLaMA and Mistral models via CrewAI, with all data remaining inside the agency's infrastructure. The source reports a significant reduction in manual effort and promising pilot results, without figures.
This entry has 13 published fields tied to exact passages in an immutable source capture.
Inspect the highlighted sourceThe challenge
With limited staff capacity and increasing digital workloads, the BA needed a scalable solution for processing Jira tickets that maintained quality and privacy standards.
The solution
Capgemini and the BA built a coordinated system of specialised AI agents: a reader agent extracts information from RFCs and user stories, a planner agent breaks the task into steps, a creator agent generates the Jira ticket, and a reviewer agent checks for consistency and duplicates before a human gives final approval. Aleph Alpha, LLaMA and Mistral models are orchestrated via CrewAI, entirely on-premises in the BA's local Jira instance.
Reported business value
The source reports that automated ticket creation works smoothly in most cases, significantly reducing manual effort, and describes initial pilot results as highly promising; it gives no figures.
Sources
Open any source and check the claim yourself — that is the point of the register.
This record was researched and written with AI assistance, and its claims were checked against the sources above. (EU AI Act art. 50 transparency notice.)
Other government & public sector entries in the register.
GovTech unlocks data insights to improve nationwide services with Databricks
Singapore's Government Technology Agency (GovTech) migrated from an on-premises dashboarding system to the Databricks Data + AI Platform on AWS with Unity Catalog and Delta Lake, cutting dashboard creation time from 90 to 30 days, democratizing data across 50% of corporate divisions in the first year, and saving 8,000 labor hours annually.
Estonia rolls out Bürokratt, an AI-guided virtual assistant network for public services
Bürokratt is a network of chatbots deployed on Estonian public sector institutions' websites, letting people obtain information from institutions and use public and information services via virtual assistants. It is a state-created, AI-based digital assistant that helps institutions deliver modern, efficient, around-the-clock customer service using large language models.
City of Helsinki pilots watsonx.ai for multilingual customer care chatbot translation
The City of Helsinki collaborated with IBM Client Engineering and IBM Consulting on a Proof of Value testing whether IBM watsonx.ai could translate foreign-language questions into Finnish for its customer care chatbot, which supports Finnish, English, and Swedish. Watsonx.ai scored 0.90 on the COMET machine-translation metric for English-to-Finnish translation (versus 0.91 for the incumbent system) and 0.87 for Swedish-to-Finnish (versus 0.86), performing on par with the city's existing translation solution.
Madrid builds VisitMadridGPT on Azure OpenAI to answer tourists in 95+ languages
The City of Madrid, with partner iUrban, built the VisitMadridGPT virtual assistant on Microsoft Azure OpenAI Service to give tourists accurate, real-time, personalized information in more than 95 languages, drawing from the city's official tourism content. Users average 2.8 questions and spend about 4 minutes 18 seconds per session with a low bounce rate, and the city analyzes assistant conversations to identify popular topics and refine its digital marketing strategy.
Was this helpful?
Your feedback helps us improve our use case database
