Codex with GPT-5.5 Speeds Up Code Review at Ramp

Ramp engineers use Codex with GPT‑5.5 to get substantive pull‑request feedback in minutes instead of hours and to build internal agentic tooling such as On‑Call Assistant, demonstrating how the model’s reasoning capabilities reduce manual work and accelerate development.

Code Review Acceleration

Codex with GPT‑5.5 provides Ramp engineers with rapid, thorough pull‑request feedback that replaces hours‑long waits with minutes of review. Thanks to its reasoning capabilities, Codex with GPT‑5.5 reduces the amount of manual, hands‑on work engineers would otherwise have to do.

“Codex code review catches things that I miss and that other engineers miss and that other AI code reviewers definitely miss.” —Austin Ray, AI DevEx at Ramp

Codex code review is described as an industry gold standard that Ramp has relied on for a long time; engineers ask for it by name, look forward to its comments on every PR, and it has become a mandatory part of many code review flows. Engineers who used to wait hours for a first review can now get substantive feedback from Codex in minutes. Codex stands apart from other tools because it deeply reasons against the codebase, resulting in a level of thoroughness that most human reviewers don’t have time for. The tool meets engineers where they are: those who prefer to work close to the metal can use the CLI, while the Codex app offers visual cues, utilities, and additional features for those who want them. Ray, typically a CLI user, felt drawn to the app, saying “It feels like the app shepherds you toward higher productivity in your engineering workflows.”

“Codex with GPT-5.5 is incredibly adept at dealing with that complexity in a way that would take me a ton of mental effort, a lot of sleep, and a lot of single-minded focus on the problem to figure out.” —Austin Ray, AI DevEx at Ramp

Internal Agentic Tooling Development

Using Codex with GPT‑5.5, Ramp’s AI DevEx team has accelerated the creation of On‑Call Assistant, an agentic tool that alleviates on‑call burdens. On call is hard because it involves a lot of business logic, domain knowledge, and heavy incidents that require keeping many things in context and reasoning through complexity. For an engineer, this demands significant mental effort and single‑minded, unbroken focus. There is plenty of complexity, including concurrency bugs, a tricky balance between external and internal events, and long‑running incident investigations with evolving details that must be kept in mind. With Codex, Ray can depend on its “incredibly adept” reasoning capabilities to support development. As a result, On‑Call Assistant has become significantly faster to build, and Ray is more confident about every improvement shipped.

“Our product surface area is pretty immense,” Ray says. “Codex with GPT‑5.5 handles it like it’s nothing.”

Leadership Lessons for AI Adoption

Austin Ray advises leaders to drive AI tool adoption by demonstrating hands‑on value, building trust through guided first experiences, and maintaining a tight feedback loop with the vendor. Ray evaluates all developer tools, including AI‑driven ones, through the lens of whether they actually change how people ship code or are merely a demo. He recommends the following for other leaders:

• Demonstrate the potential of AI tools first‑hand: “Get your engineers to install Codex, sit down with them, and guide them through a really solid first session. Paint the picture of what development could be for them.”
• Build a path to trust and iteration: “Most engineers don’t fully understand or trust that they’re going to have a good experience with this. They treat it as something experimental. By guiding them through that first experience, you change their perspective and make them willing to explore and iterate themselves until they become one of your best AI users.”
• Invest in the feedback loop: “We work directly with the Codex team on feedback. When we hit issues, we have a direct line. That feedback loop is what makes a vendor relationship worth investing in, and we’ve made incredible progress with the Codex team.”

  “Codex is the real deal. Codex definitely helps us ship faster.” —Austin Ray, AI DevEx at Ramp

Future Outlook: Engineers as Orchestrators

Codex is changing how fast Ramp engineers can work and giving them the resources to support even greater ambitions. For Ray, this indicates a new way to think of engineering as a whole.

“Engineers are going to become orchestrators. The skill is no longer writing every line of code yourself. It’s knowing how to direct AI tools like Codex, when to trust them, and when to push back. At Ramp, our best engineers learn that fastest.”