Cisco is working with OpenAI and its newly released Codex software engineering agent to give network engineers access to better tools for writing, testing and building code.
Codex is an AI coding agent available via ChatGPT that can navigate a codebase, implement and test code changes, and propose pull requests for review, according to Jeetu Patel, Cisco’s president and chief product officer.
“We are exploring how Codex can help our engineering teams bring ambitious ideas to life faster,” Patel wrote in a blog post. “As early design partners, Cisco is helping shape the future of Codex by evaluating it for real-world use cases across our product portfolio and providing feedback to the OpenAI team.”
According to OpenAI and ChatGPT, Codex could be embedded into Cisco management tools to auto-generate configuration scripts for routers, switches and firewalls and to troubleshoot network security and performance issues.
OpenAI describes Codex as a cloud-based software engineering agent that can work on many tasks in parallel. “Codex can perform tasks for you such as writing features, answering questions about your codebase, fixing bugs, and proposing pull requests for review; each task runs in its own cloud sandbox environment, preloaded with your repository,” OpenAI stated in a blog post about the agent.
How Codex works
Codex can be accessed through the sidebar in ChatGPT, and users can assign it new coding tasks by typing a prompt and clicking “Code”.
“If you want to ask Codex a question about your codebase, click “Ask”. Each task is processed independently in a separate, isolated environment preloaded with your codebase. Codex can read and edit files, as well as run commands including test harnesses, linters, and type checkers. Task completion typically takes between 1 and 30 minutes, depending on complexity, and you can monitor Codex’s progress in real time,” according to OpenAI.
“Once Codex completes a task, it commits its changes in its environment. Codex provides verifiable evidence of its actions through citations of terminal logs and test outputs, allowing you to trace each step taken during task completion,” OpenAI wrote. “You can then review the results, request further revisions, open a GitHub pull request, or directly integrate the changes into your local environment. In the product, you can configure the Codex environment to match your real development environment as closely as possible.”
OpenAI is releasing Codex as a research preview: “We prioritized security and transparency when designing Codex so users can verify its outputs – a safeguard that grows increasingly more important as AI models handle more complex coding tasks independently and safety considerations evolve. Users can check Codex’s work through citations, terminal logs and test results,” OpenAI wrote.
Internally, technical teams at OpenAI have started using Codex. “It is most often used by OpenAI engineers to offload repetitive, well-scoped tasks, like refactoring, renaming, and writing tests, that would otherwise break focus. It’s equally useful for scaffolding new features, wiring components, fixing bugs, and drafting documentation,” OpenAI stated.
Cisco’s view of agentic AI
Patel stated that Codex is part of the developing AI agent world, where Cisco envisions billions of AI agents will work together to transform and redefine the architectural assumptions the industry has relied on. Agents will communicate within and across data centers, and across every place we live, work, and connect with customers— all at incredible speed, scale and efficiency, Patel said.
Cisco’s advanced research outfit Outshift recently proposed an Internet of Agents, an open-sourced, three-layer architecture that would allow AI agents to collaborate autonomously and share complex reasoning, the vendor stated.
AI agents are fundamentally different, Vijoy Pandey, senior vice president of Outshift by Cisco, recently told Network World. “They don’t just share information; they collaborate, reason, and take autonomous actions in real-time. More importantly, they introduce probabilistic computing into our technological foundation,” Pandey said.
“As AI gets built into every application and service, organizations will find themselves managing hundreds or thousands of discrete agents. Without open standards and frameworks, this diversity creates chaos,” Pandey said. “It’s like the early days of networking – we need common protocols and standards so these agents can discover, communicate, and collaborate with each other effectively. This standardization and interoperability will be essential for enterprises to effectively manage and scale their AI initiatives.”
Codex is a $200-a-month service available to ChatGPT Pro subscribers. It offers access to all of OpenAI’s latest tools, the company said. OpenAI also plans to offer Codex through its other paid services.