October 13, 2026Online track1 min readLivestream excerpt

Agents in Orbit: Workflows, Not Autopilot

Flywire’s Orbit brings engineering agents into an existing GitLab and AWS environment. This opening excerpt covers the company’s infrastructure and privacy constraints before the livestream returns to the live stage.

Eduardo SimonFlywire

Javier CasalFlywire

From the conference livestream · 5:06:03–5:08:21 on YouTube. Interrupted livestream excerpt (2 minutes). The reading edition links the complete recording.

5:06:03 ↗

A platform built inside the existing engineering environment

Flywire processes complex payments across education, healthcare, travel, and business services. That makes the placement of an engineering agent consequential: customer information and payment details cannot simply be handed to an outside service without governance.

Eduardo Simon introduces the work of Flywire's AI Platform Experience team alongside Javier Casal. The team's aim is practical agentic infrastructure that follows the company's existing engineering standards. Simon describes an organization of roughly 400 engineers working across Java, Ruby, Go, Python, .NET, and PHP, with most systems deployed through Victoria, an internal platform built on GitLab and AWS. 5:06:03

Orbit aims to remove repetitive engineering work within that environment. It has to follow the same engineering standards and controls as the systems it helps operate.

The livestream cuts away before the architecture is explained. This opening excerpt ends there; the complete presentation continues Simon and Casal's account of how Orbit works.

Further reading

Full transcript 25 timestamped passages

Machine transcription with reviewed terminology and names. Some recognition errors may remain. Timestamps refer to the original livestream.

5:06:03Hello everyone and welcome. My name is Edu and alongside Javi, we represent the AI Platform

5:06:09Experience team at Flywire. Our core mission is to build practical agentic infrastructure

5:06:14that empowers our software engineers while following our established engineering standards

5:06:19and practices. Today, we'll share how structured workflow automation delivers real enterprise value,

5:06:26ensuring control, safety, and reliability across our development process.

5:06:31Before we dive into the deep technical details of our AI platform, let us give you some essential

5:06:37context about Flywire. Flywire is built to process the world's most complex payments

5:06:43across global industries like education, healthcare, travel, and business services.

5:06:49Today, we serve over 5,000 clients across more than 240 countries around the world.

5:06:55Because we process high-value international transactions,

5:06:59regulatory compliance, privacy, and security are not optional add-ons.

5:07:04They are core requirements of our business.

5:07:06We operate under strict compliance frameworks like PCI, DSS, and SOC2.

5:07:13This means that customer data, personal identification, and payment details must remain completely safe.

5:07:20We cannot simply take sensitive context and pass it to third-party services without strict governance and architectural boundaries.

5:07:27To give you an idea of our engineering organization, we have around 400 software engineers distributed globally.

5:07:35Across our teams, we maintain diverse technology stacks, including Java, Ruby, Go, Python, .NET, and PHP.

5:07:46Almost everything we build and run is deployed on Victoria, our internal platform as a service that operates on top of GitLab and AWS infrastructure.

5:07:55This brings us to Orbit, our own toil killer.

5:07:58Orbit is an internal platform that eliminates daily engineering.

5:08:02It's called only where we talk every day.

5:08:04It also gives the code that the other AI services and tools we use across Flywire can start

5:08:10workflows directly. For example, an engineer will be able to ask Claude in Slack use cases.

5:08:16Send prices can start workflows directly.

5:08:19Victoria, it starts...