{
  "schema_version": "1.1",
  "id": "archive:https://openai.com/business/customer-stories/revolut",
  "slug": "revolut-1vgkrx3",
  "url": "https://feed7.dev/p/revolut-1vgkrx3",
  "title": "How Revolut raises ambition without lowering the bar",
  "why_included": "Revolut describes using Codex agents for implementation while engineers retain design and review responsibility. Its reported time savings are a case study, but the workflow offers concrete ideas for delegation and guardrails.",
  "summary": "Revolut reports **30–60% less coding time** from task start to feature merge with Codex. One engineer split an internal code-review service into agent tasks; the company also turned roughly **seven years of design documentation into AI-readable context in one day** and reports saving one to two days on a substantial security review.\nFor builders, delegate bounded implementation or investigation work while keeping a person responsible for reviewing source evidence and understanding code changes. Map what each agent can see, which tools it can use, and what happens when a step fails.\nThese figures come from Revolut's account and are not a controlled comparison. The material does not give details about task mix, review overhead across all projects, or how results transfer to smaller teams.",
  "practical_implication": "",
  "agent_context": "Revolut reports **30–60% less coding time** from task start to feature merge with Codex. One engineer split an internal code-review service into agent tasks; the company also turned roughly **seven years of design documentation into AI-readable context in one day** and reports saving one to two days on a substantial security review.\nFor builders, delegate bounded implementation or investigation work while keeping a person responsible for reviewing source evidence and understanding code changes. Map what each agent can see, which tools it can use, and what happens when a step fails.\nThese figures come from Revolut's account and are not a controlled comparison. The material does not give details about task mix, review overhead across all projects, or how results transfer to smaller teams.",
  "source": {
    "name": "OpenAI",
    "url": "https://openai.com/business/customer-stories/revolut",
    "published_at": "2026-11-16T09:30:00.000Z"
  },
  "source_class": "blog_post",
  "content_type": "Official Release",
  "layer": "agent",
  "domains": [
    "coding",
    "security"
  ],
  "topics": [
    "coding-agents",
    "multi-agent",
    "harness-engineering"
  ],
  "verification": {
    "status": "official_source",
    "label": "Official Source",
    "method": "source_feed",
    "verified_at": null
  },
  "uncertainty": [],
  "connected_context": {
    "meaning": "Revolut’s reported time savings add a company-specific example of agent-assisted delivery, with bounded task delegation and review alongside context preparation. The account illustrates a possible workflow, but its figures do not show how much comes from the agents versus process changes or how well the results transfer to a smaller team.",
    "corpus_size": 1116,
    "generated_at": "2026-11-18T11:08:05.572Z",
    "connections": [
      {
        "title": "From AI-Assisted to AI-Native: Building a Frontier Development Team — Clare Liguori, AWS",
        "source_name": "AI Engineer",
        "source_url": "https://www.youtube.com/watch?v=pqlWNihgdjI",
        "feed7_url": "https://feed7.dev/p/from-ai-assisted-to-ai-native-building-a-frontier-development-team-clare-0n539qm",
        "reason": "The AWS pilot identifies agent-readable context, fast feedback, scoped work, and parallelism as workflow conditions behind team gains; these provide possible mechanisms to examine alongside Revolut’s reported savings, not proof of their cause."
      },
      {
        "title": "Building a software factory for AI SDK",
        "source_name": "Vercel",
        "source_url": "https://vercel.com/blog/building-a-software-factory-for-ai-sdk",
        "feed7_url": "https://feed7.dev/p/building-a-software-factory-for-ai-sdk-0udhuk3",
        "reason": "Vercel describes narrow agent tasks, evidence, and human merge authority as operational controls for scaling delivery. That complements Revolut’s bounded delegation and review while offering no independent validation of its time-saved figures."
      },
      {
        "title": "CodeRabbit scales agentic software development and ships 20x more",
        "source_name": "OpenAI",
        "source_url": "https://openai.com/index/coderabbit-codex-daybreak",
        "feed7_url": "https://feed7.dev/p/coderabbit-codex-daybreak-1dtbewo",
        "reason": "CodeRabbit also reports increased delivery alongside changes to review and release workflows. The two company accounts reinforce that throughput claims involve process changes, while neither establishes a controlled productivity effect."
      }
    ]
  },
  "lifecycle": "Current",
  "published_at": "2026-11-16T09:30:00.000Z",
  "modified_at": "2026-11-16T09:30:00.000Z",
  "supersedes": [],
  "expires_at": null,
  "formats": {
    "html": "https://feed7.dev/p/revolut-1vgkrx3",
    "json": "https://feed7.dev/p/revolut-1vgkrx3.json",
    "markdown": "https://feed7.dev/p/revolut-1vgkrx3.md"
  }
}