Blab Tech
Mercedes-Benz Uses Atlassians Teamwork Graph and Rovo AI to Cut Vehicle Defect Fix Times
Mercedes‑Benz announced that it has leveraged Atlassian’s Teamwork Graph and the Rovo AI platform to streamline how defects discovered during vehicle testing are filed and resolved. The move, showcased at Atlassian’s Team ’26 conference in a session titled “How Mercedes turns Teamwork Graph into an AI advantage,” aims to shrink the interval between defect detection on a test vehicle and its fix.
Large enterprises often juggle work across dozens of tools. Mercedes‑Benz’s engineering teams rely on more than 300 SaaS applications, a fact highlighted in Atlassian’s blog post. Engineers must hop between systems that hold requirements, code, release data, physical part details, and telemetry from test runs. When a defect is reported, the lack of a unified context can trigger several rounds of back‑and‑forth before the right team takes ownership and a solution is found.
To break this cycle, Mercedes‑Benz wired its data sources into the Teamwork Graph, Atlassian’s data‑intelligence layer. The graph ties a defect to the requirement it traces to, the code that implements it, and the vehicle configuration where the fault surfaced. By making these relationships traversable, AI agents can retrieve all pertinent information with a single query.
The company built a family of AI agents in Rovo—informally dubbed the “Norris family.” Defect Norris conducts quality‑assurance checks at intake. Analyze the Snores pulls log data and telemetry for the specific vehicle and event. A cross‑vehicle‑line analysis agent checks whether a defect found in one model might affect other models that share components or software. Main Norris manages regulatory and safety context.
One practical hurdle was filing a defect while driving. Engineers on the Autobahn can’t stop to open a ticket. Mercedes‑Benz therefore created an in‑car voice application that lets engineers describe a defect using natural speech while in motion. The app converts speech to text, associates the description with the vehicle identification number, and forwards the data to Jira. Defect Norris then structures the information into a complete defect record, adding metadata, component identification, and linked vehicle data.
The new workflow delivered measurable gains. Mercedes‑Benz measured lead time from defect detection to resolution and found a 70% reduction compared to the previous approach. The baseline was set during the development of the new S‑Class before the new workflow was deployed.
Mercedes‑Benz’s experience underscores that enterprise AI must operate across tools and teams, not just at the individual level. Richer context, workflow participation, and strict adherence to permissions proved essential for AI to deliver value at scale.
Looking ahead, the company plans to expand the approach beyond defect management. The broader ambition is a digital twin for engineering work, where AI powered by the Teamwork Graph handles 80‑90% of routine effort, freeing engineers to focus on higher‑value tasks.
Atlassian supports this model by offering more than 100 out‑of‑the‑box connectors that bring data from proprietary or legacy systems into the graph. Organizations can build custom connectors to integrate their own tools. Once data is ingested, it becomes searchable and actionable across Atlassian products and can power custom agents.
The initiative demonstrates how an automotive manufacturer can use AI and graph technology to cut defect resolution times and improve overall quality. It also highlights the importance of a shared data layer for enterprise AI to succeed.
The project was announced in a blog post by Atlassian and showcased at the Team ’26 conference. The post cites product manager Tobias Langjahr, who explained that the average large enterprise runs over 367 SaaS applications and that complexity can increase when AI is added without a shared context.
Mercedes‑Benz’s work fits a broader trend of automotive companies integrating AI into production and quality‑control processes. Other reports indicate that Mercedes is also testing AI‑enhanced humanoid robots on its production lines, further illustrating the company’s commitment to automation.
In summary, Mercedes‑Benz’s use of Atlassian’s Teamwork Graph and Rovo AI to streamline defect management has cut lead times by 70%, improved data integration across tools, and set a foundation for future AI‑driven engineering workflows.
Large enterprises often juggle work across dozens of tools. Mercedes‑Benz’s engineering teams rely on more than 300 SaaS applications, a fact highlighted in Atlassian’s blog post. Engineers must hop between systems that hold requirements, code, release data, physical part details, and telemetry from test runs. When a defect is reported, the lack of a unified context can trigger several rounds of back‑and‑forth before the right team takes ownership and a solution is found.
To break this cycle, Mercedes‑Benz wired its data sources into the Teamwork Graph, Atlassian’s data‑intelligence layer. The graph ties a defect to the requirement it traces to, the code that implements it, and the vehicle configuration where the fault surfaced. By making these relationships traversable, AI agents can retrieve all pertinent information with a single query.
The company built a family of AI agents in Rovo—informally dubbed the “Norris family.” Defect Norris conducts quality‑assurance checks at intake. Analyze the Snores pulls log data and telemetry for the specific vehicle and event. A cross‑vehicle‑line analysis agent checks whether a defect found in one model might affect other models that share components or software. Main Norris manages regulatory and safety context.
One practical hurdle was filing a defect while driving. Engineers on the Autobahn can’t stop to open a ticket. Mercedes‑Benz therefore created an in‑car voice application that lets engineers describe a defect using natural speech while in motion. The app converts speech to text, associates the description with the vehicle identification number, and forwards the data to Jira. Defect Norris then structures the information into a complete defect record, adding metadata, component identification, and linked vehicle data.
The new workflow delivered measurable gains. Mercedes‑Benz measured lead time from defect detection to resolution and found a 70% reduction compared to the previous approach. The baseline was set during the development of the new S‑Class before the new workflow was deployed.
Mercedes‑Benz’s experience underscores that enterprise AI must operate across tools and teams, not just at the individual level. Richer context, workflow participation, and strict adherence to permissions proved essential for AI to deliver value at scale.
Looking ahead, the company plans to expand the approach beyond defect management. The broader ambition is a digital twin for engineering work, where AI powered by the Teamwork Graph handles 80‑90% of routine effort, freeing engineers to focus on higher‑value tasks.
Atlassian supports this model by offering more than 100 out‑of‑the‑box connectors that bring data from proprietary or legacy systems into the graph. Organizations can build custom connectors to integrate their own tools. Once data is ingested, it becomes searchable and actionable across Atlassian products and can power custom agents.
The initiative demonstrates how an automotive manufacturer can use AI and graph technology to cut defect resolution times and improve overall quality. It also highlights the importance of a shared data layer for enterprise AI to succeed.
The project was announced in a blog post by Atlassian and showcased at the Team ’26 conference. The post cites product manager Tobias Langjahr, who explained that the average large enterprise runs over 367 SaaS applications and that complexity can increase when AI is added without a shared context.
Mercedes‑Benz’s work fits a broader trend of automotive companies integrating AI into production and quality‑control processes. Other reports indicate that Mercedes is also testing AI‑enhanced humanoid robots on its production lines, further illustrating the company’s commitment to automation.
In summary, Mercedes‑Benz’s use of Atlassian’s Teamwork Graph and Rovo AI to streamline defect management has cut lead times by 70%, improved data integration across tools, and set a foundation for future AI‑driven engineering workflows.
