Cisco and OpenAI redefine enterprise engineering with AI age…

数十年来， Cisco 一直构建并运行着一些世界上最复杂、最关键的生产级软件系统。随着生成式人工智能从试验走向可投入实际运行的能力， Cisco 把擅长的事情做到了极致：在苛刻的真实环境中放大并部署先进技术。

基于这一思路， Cisco 开始与 OpenAI 紧密合作，将 Codex 推向企业级软件工程的实际应用，帮忙界定什么才算“企业级”的 AI 工具，以及如何把 Codex 应用于复杂生产环境里的大规模工程工作。

Cisco 并没有把 Codex 当作单纯的开发者工具，而是直接将其嵌入到生产工程工作流中，让它处理大规模的多仓库系统、以 C/C++ 为主的代码库，以及全球化企业所需的安全、合规与治理要求。

在这一过程中， Cisco 把 Codex 打造得不同于传统的开发效率工具：它成为一个能在企业级规模中协作的 AI 工程队友。

“我很享受把 Codex 集成进 Cisco 企业软件生命周期工作流中不断发现的新机会。与 OpenAI 团队合作，使 Codex 达到企业生产就绪状态，也很有成就感。”
— Ching Ho， Cisco 工程领导团队成员

评估具有代理能力的 AI 在复杂代码库中的表现

Cisco 本身已经拥有成熟的工程体系，并同时推进多项 AI 计划。让 Codex 有吸引力的，不是简单的代码补全或表面自动化，而是其“代理”能力：它能够

• 在大型、相互连接的代码仓库间进行理解与推理；
• 在复杂语言中流畅工作；
• 通过基于 CLI 的自主编译—测试—修复循环执行真实工作流；
• 在现有的代码评审、安全与治理框架内运作。

通过与 OpenAI 的直接合作， Cisco 工程师得以把在真实环境中观察到的反馈传回去，促成在工作流编排、安全控制以及对长时间运行工程任务的支持等方面的改进——这些都是企业级使用的关键要素。

把 Codex 用于关键工程工作流

当 Codex 被嵌入日常工程工作后，团队开始把它用于一些最具挑战性、最耗时的流程：

• 跨仓库构建优化： Codex 分析了超过 15 个相互关联的仓库的构建日志和依赖图，识别出低效环节。结果是构建时间约缩短了 20%，在全球范围内每月节省了 1500 多小时的工程工作量。
• 大规模缺陷修复（ CodeWatch ）：借助 Codex-CLI ， Cisco 在大规模 C/C++ 代码库上实现了迭代、具代理性的自动缺陷修复。原本需要数周的人工工作现在可在数小时内完成，缺陷解决吞吐量提高了 10–15 倍，让工程师有更多时间专注设计与验证。
• 框架迁移由数周缩短为数天：当 Splunk 团队需要将多个界面从 React 18 迁移到 React 19 时， Codex 自主完成了大量重复性修改，将数周工作压缩到数天，使工程师得以把精力放在需要判断的关键决策上。

“最明显的收益来自于我们不再把 Codex 当作一个工具，而是把它当成团队的一份子。我们让 Codex 生成并执行一份计划文档，审查团队因此能更容易理解流程和生成的代码。”
— Ryan Brady， Cisco Splunk 团队资深工程师

为企业化路线图提供方向

来自生产环境的持续反馈帮助 OpenAI 加速了 Codex 在大型企业场景下的成熟，特别是在合规、长时任务管理以及与现有开发流水线集成等方面。

对 Cisco 来说，这次合作确立了一套可复制的下一代 AI 采纳模式：从第一天起就建立深度技术伙伴关系、用真实工作负载检验，并获得高层领导的对齐支持。

“ Codex 已成为我们思考未来 AI 辅助开发与运维方式时的重要组成部分。”
— Brad Murphy，负责 Cisco Splunk 工程的副总裁

未来数月， Cisco 与 OpenAI 将继续在 Codex 及更广领域保持密切合作，推进双方在企业级规模上实现以 AI 为原生的工程实践。

For decades, Cisco has built and operated some of the world’s most complex, mission-critical software systems. As generative AI matured from experimentation to real operational capability, Cisco leaned into what it knows best: scaling advanced technology inside demanding, real-world environments.

That mindset led Cisco to begin working closely with OpenAI around Codex, helping define what enterprise-grade AI for software engineering should look like in practice—and how Codex could be applied to real, large-scale engineering work inside complex production environments.

Rather than treat Codex as a standalone developer tool, Cisco began integrating it directly into production engineering workflows, exposing it to massive multi-repository systems, C/C++-heavy codebases, and the security, compliance, and governance requirements of a global enterprise.

In the process, Cisco helped shape Codex into something fundamentally different from a developer productivity tool: an AI engineering teammate capable of operating at enterprise scale.

"I’ve loved discovering new opportunities to integrate Codex into Cisco's enterprise software lifecycle workflows. Collaborating with the OpenAI team to get Codex enterprise production ready has been rewarding as well."

Evaluating agentic AI in complex codebases

Cisco already runs a mature engineering organization with multiple AI initiatives in flight. What made Codex compelling wasn’t code completion or surface-level automation, but agency. Codex demonstrated the ability to:

• Understand and reason across large, interconnected repositories
• Work fluently in complex languages
• Execute real workflows through CLI-based, autonomous compile-test-fix loops
• Operate within existing review, security, and governance frameworks

By working directly with OpenAI, Cisco engineers were able to give feedback on how these capabilities behaved in real environments, shaping areas like workflow orchestration, security controls, and support for long-running engineering tasks—all of which are critical for enterprise use.

Using Codex for critical engineering workflows

Once Codex was embedded into everyday engineering work, teams began applying it to some of their most challenging and time-consuming workflows:

Cross-repo build optimization: Codex analyzed build logs and dependency graphs across more than 15 interconnected repositories, identifying inefficiencies. The result: a ~20% reduction in build times and more than 1,500 engineering hours saved per month across global environments.

Defect remediation at scale (CodeWatch): Using Codex-CLI, Cisco automated defect repair with iterative, agentic execution on large-scale C/C++ codebases. What once took weeks of manual effort now completes in hours, delivering a 10-15× increase in defect resolution throughput and freeing engineers to focus on design and validation.

Framework migrations in days, not weeks: When Splunk teams needed to migrate multiple UIs from React 18 to 19, Codex handled the bulk of repetitive changes autonomously, compressing weeks of work into days and allowing engineers to concentrate on judgment-heavy decisions.

“The biggest gains came when we stopped thinking about Codex as a tool and started treating it as part of the team. We use Codex to generate and follow a plan document, allowing the reviewing team to more easily understand both the process and the code generated.”

Shaping Codex's roadmap for the enterprise

Cisco provided continuous feedback from real production use that helped OpenAI accelerate Codex’s readiness for large enterprises—particularly in areas like compliance, long-running task management, and integration with existing development pipelines.

For Cisco, the collaboration established a repeatable model for adopting next-generation AI: deep technical partnership, real workloads, and leadership alignment from day one.

“Codex has become a meaningful part of how we think about AI-assisted development and operations going forward.”

In the months ahead, Cisco and OpenAI will continue to collaborate closely on Codex and beyond to advance their shared mission of AI-native engineering at enterprise scale.

Generated by RSStT. The copyright belongs to the original author.

Source