Cognizant and Cognition said autonomous artificial intelligence (AI) engineering work at logistics provider Odyssey Logistics is now in production, with Odyssey reporting a 37% net cost saving against a conventional modernisation approach.
Cognizant said the project used Cognition’s AI software engineer Devin alongside its engineers to rebuild legacy applications supporting Odyssey’s transportation management operations.
Odyssey is currently working to launch its OdysseyONE platform, which is aims to support order intake, execution, visibility, and lifecycle management across its network. According to Cognizant, the modernisation involved moving workflow logic from legacy Microsoft Access and
Visual Basic for Applications forms while preserving the original business rules.
A seven-person Cognizant team used Devin for the legacy conversion, rebuilding the forms as cloud-native applications and generating tests, deployment pipelines, and documentation alongside the code. Cognizant said every change was reviewed and signed off by a technical lead or architect before merging.
"Software engineering is changing faster than anything I have seen in my career," Tarun Kumar, Americas Head, Software Engineering Group at Cognizant, said in a statement. "Autonomous agents change the economics of modernisation and what an enterprise can realistically do."
Cognizant said delivery throughput rose by roughly a third and Odyssey recorded a 37% net cost saving against the conventional approach. The company said the current phase is live.
Before committing to the redevelopment, Odyssey tested the approach with Cognizant and Devin on a separate standalone legacy application. According to the companies, that project closed 21 days after kickoff, after which Odyssey applied the approach to its transportation management platform, which is now in production.
"Modernisation only matters if it changes the business outcome," said Maneet Singh, CIO and CDO at Odyssey Logistics. "For us, this was about moving faster without compromising discipline."
Cognizant has trained more than 3,000 associates on Devin. Based on Cognizant's internal data, the company said Devin reduced time to release-ready code by more than 50% and accelerated greenfield development five to six times.
The companies said their broader collaboration now includes a modernisation and upgrade offering, a quality engineering offering that uses Devin to identify test-coverage gaps and assist with test generation, and a ‘Frontier AI Cyber Defense’ offering. They also aim to explore applications in security remediation, AI assurance, application maintenance, legacy modernisation, and greenfield software development.


Your reaction
Discussion
What's your take on this story?
No comments yet — be the first to share your view.