An independent publicationEvery case sourced, dated & graded A–DGet the weekly Casefile →
Grade BproductionSource date Oct 17, 2026· Last verified Oct 17, 2026

How is Itaú using the Devin coding agent across its software lifecycle?

Itaú Unibanco · Banking & Financial Services

Header image: A clinician working on a laptop and tablet with a stethoscope

Itaú Unibanco, Brazil's largest bank, rolled out Devin across its software development lifecycle. Cognition reports a .NET to Java migration of 59 services 6x faster at 5x lower cost, ~70% of scanner-flagged vulnerabilities resolved automatically, and test coverage raised from ~50% to ~90+%.

Reported outcomes

service migration
59 services migrated 6x faster at 5x lower cost
Source [1] · self-reported
vulnerability remediation
~70% resolved automatically
Source [1] · self-reported
test coverage
from ~50% to ~90+%
Source [1] · self-reported

Outcomes are reported exactly as stated by the source; we have not independently audited them.

How it works

  1. Devin performs code migrations (.NET to Java, SQL Server objects).
  2. Automatically fixes vulnerabilities flagged by SonarQube, Fortify, and Veracode.
  3. Generates tests to raise coverage.

Risks & compliance

  • Agent-written code requires review
  • Vendor-published results
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.

All tools by category →

Sources

[1]Cognition (Devin)· vendor customer story· Undated (accessed Oct 17, 2026)
“~70% of vulnerabilities from SonarQube/Fortify/Veracode resolved automatically.”
How Itaú Deployed AI Across the SDLC at Global-Finance Scale

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 3/3 outcome claims matched the source. Compiled by the Agent Casefile research desk (AI-assisted; see methodology). Spot an error? Request a correction.

Keep reading

Related cases