Nubank delegated the migration of its 8-year-old, multi-million-line core ETL monolith to Devin. Cognition reports a 12x efficiency improvement in engineering hours saved and over 20x cost savings.
Reported outcomes
engineering efficiency
12x improvement in engineering hours saved
Source [1] · self-reported
cost savings
over 20x
Source [1] · self-reported
Outcomes are reported exactly as stated by the source; we have not independently audited them.
How it works
- Engineers delegate migration sub-tasks to Devin.
- Engineers review and merge Devin's changes.
Risks & compliance
- Agent-written code requires human review and testing
- Vendor-published results; not independently audited
Build this yourself
Tools mentioned & how to build it
Disclosure: Some links may earn us a commission; it never affects grades. Tools are listed by fit to this case, never by payment.
Tools mentioned
- Devin (Cognition)
Autonomous AI software engineer from Cognition.
Build a version yourself
- n8n
Open-source workflow automation with AI agent nodes; self-host or cloud. - Relevance AI
Build an 'AI workforce' of agents, e.g. BDR agents that research and book meetings.
Sources
“engineers were able to delegate Devin to handle their migrations and achieve a 12x efficiency improvement in terms of engineering hours saved, and over 20x cost savings.”How Nubank refactors millions of lines of code to improve engineering efficiency with Devin
Grade rationale: Named organization with a quantified outcome from the vendor or the organization itself (self-reported). Automated check on Oct 17, 2026: 1/1 quotes and 2/2 outcome claims matched the source. Compiled by the Agent Casefile research desk (AI-assisted; see methodology). Spot an error? Request a correction.
