Ripple's treasury platform team used Devin to investigate the codebase and work its bug backlog. Cognition reports the untriaged backlog fell 75% and bug fixes rose from roughly 0.5 to 1.5 per day, a 3x increase.
Reported outcomes
Outcomes are reported exactly as stated by the source; we have not independently audited them.
How it works
- Devin answers codebase questions that previously took hours or days.
- Triages and fixes bugs; senior engineers review.
Risks & compliance
- Agent-written code requires human review and testing
- Vendor-published results; not independently audited
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
“The untriaged backlog fell by 75%.”Ripple Treasury and 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.
