🧵

Devin @ Nubank (ETL migration)

Self-ReportedCurated

Human-orchestrated Devin fleet — 8-12x efficiency on a 6M-LoC migration.

Cognition· Operating since Dec 1, 2024· active
Curated from Cognition — Devin at Nubank case study — not claimed by or endorsed by the organization. Metrics cited only as the source states. Absent metrics render as [unknown].

Recent activity

Version cuts and proof, newest first — the living track record.

  1. Artifact · Devin @ Nubank case study published (Cognition + Nubank)1y ago

Spec sheet

The benchmark fields — designed for comparison across teams.

Topology
Orchestrator–Worker
Agent count
1
Platform
Devin
Runs on
Devin
Industries
fintech
Task kinds
code-migration
Trust tier
Self-Reported
Proof entries
1

Topology & roster

Orchestrator–Worker

Orchestrator-worker with a human orchestrator. A human PM/engineer team prompts, reviews, and approves many parallel Devin instances working decomposed migration subtasks; there is no AI orchestrator agent in this pattern.

System wiring

Typical Orchestrator–Worker layout — schematic, not verified wiring
Node details

Typical Orchestrator–Worker layout — schematic, not verified wiring

HumanHuman operatorHuman gate
Tool
Human operator
Autonomy
Human-gated
Sends
  • directs → Orchestrator
OrchestratorOrchestrator
Tool
Orchestrator
Autonomy
Runs autonomously
Sends
  • dispatches → Worker agent
  • requests gate → QA reviewer
Receives
  • directs ← Human operator
BuilderWorker agent
Tool
Worker agent
Autonomy
Runs autonomously
Sends
  • commits to → Shared workspace
Receives
  • dispatches ← Orchestrator
QAQA reviewer
Tool
QA reviewer
Autonomy
Runs autonomously
Sends
  • gate verdict → Shared workspace
Receives
  • requests gate ← Orchestrator
ResourceShared workspace
Tool
Shared workspace
Autonomy
Runs autonomously
Receives
  • commits to ← Worker agent
  • gate verdict ← QA reviewer

How a typical Orchestrator–Worker team handles a task

Typical Orchestrator–Worker layout — schematic, not verified wiring

  1. Task arrives

    Human operator directs Orchestrator.

  2. The orchestrator routes the work

    Orchestrator dispatches build work to Worker agent.

  3. Worker agent builds the work

    Worker agent builds the work.

  4. Independent review gates the work

    QA reviewer reviews the work. This reviewer is autonomous and separate from the agent that built the work, so the check is independent of its author.

  5. The artifact lands

    The artifact lands in Shared workspace: Worker agent contributes via "commits to" and QA reviewer contributes via "gate verdict".

  6. Human holds the last word

    Human operator holds final approval.

Replicate a typical Orchestrator–Worker setup

Typical Orchestrator–Worker layout — schematic, not verified wiring

Ingredients

  • HumanHuman operator
  • OrchestratorOrchestrator
  • BuilderWorker agent
  • QAQA reviewer
  • ResourceShared workspace

Setup order

  1. 1.Provision the substrate: Shared workspace.
  2. 2.Stand up the orchestrator: Orchestrator.
  3. 3.Wire Worker agent: it receives "dispatches" from Orchestrator. Wire QA reviewer: it receives "requests gate" from Orchestrator.
  4. 4.Give QA reviewer an independent workspace/verdict channel: "gate verdict" to Shared workspace.
  5. 5.Declare the human gate: Human operator holds final approval.

Performance metrics

Windowed metrics with provenance. [unknown] means it was not tracked — an honest hole beats an invented figure.

Cost savings vs engineer-hour
20
self-reported

'>20× cost savings' — cost of running Devin vs the hourly cost of an engineer on the delegated scope. This figure appears ONLY on the vendor (Cognition) page; Nubank's own engineering blog does not repeat it — rests on the vendor's telling alone, not independently corroborated by the customer. Parallel-instance count is [unknown] and not stated as a number anywhere. Source: devin.ai/customers/nubank, 2024-12. [self_reported]

as of Dec 1, 2024
Efficiency gain (engineering hours)
8
self-reported

'≥8× (range 8–12×)' engineering-hours efficiency gain — typical hours to complete a data-class migration task vs total hours spent prompting/reviewing Devin. Lower bound of the vendor's stated range is stored here; full range in this note. Scope: 8-year-old, 6M+ LoC monolith; ~100,000 data-class implementations; an estimated 18 months × 1,000+ engineers of work; the Data, Collections, and Risk business units each finished in weeks. Corroborated in substance by Nubank's own engineering blog (12× efficiency, weeks-not-months). Fine-tuning cut per-subtask time from ~40 to ~10 minutes — stated directly on the primary vendor page. Source: devin.ai/customers/nubank, 2024-12; building.nubank.com engineering blog, 2025-03. [self_reported]

as of Dec 1, 2024

Token economics

Cost transparency is part of the honesty architecture. [unknown] means it was not tracked — not that it is zero.

No cost metrics on record. Cost tracking is hard across runtimes; honest absence beats invented figures.

Blueprint

Operational DNA — why it works, how it was built, and how it is overseen. Not files for sale; knowledge of the design.

Why it works

Fine-tuning on prior migration examples plus a fixed human-review gate lets the fleet scale horizontally (many parallel instances) without scaling the review burden proportionally — the efficiency gain comes from parallelism bounded by a cheap human checkpoint, not from removing oversight.

How it was built

Cognition's Devin, task-specific fine-tuned on examples of prior Nubank migrations. Deployed as many parallel instances against decomposed subtasks of the ~100,000-data-class migration.

Oversight model

Human-in-the-loop by design: engineers review and approve every Devin change before it merges. This is not an autonomous pipeline — the human review step is the safety mechanism.

Proof (1)

The team's shared track record — tasks, incidents, lessons, milestones. Per-entry provenance tags are always visible.

  1. ArtifactDec 1, 2024self-reported

    Devin @ Nubank case study published (Cognition + Nubank)

    8-12x efficiency gains, >20x cost savings (vendor page only) on a 6M+ LoC ETL migration; corroborated in substance (12x, weeks-not-months) by Nubank's own engineering blog (2025-03).

    https://devin.ai/customers/nubank/

Sign in to add a proof entry.

Sign in

Attestations (0)

Named third-party statements from people with first-hand experience. Attestations are what separates Peer-Attested from Evidence-Linked.

No attestations yet. Worked with this configuration or agent? Attest to it using the form below — attestations are named third-party statements and are what separates Peer-Attested from Evidence-Linked.

Sign in to attest to this team.

Sign in