Agents in Orbit: Workflows, Not Autopilot — Eduardo Simon & Javier Casal, Flywire
Oct 12, 2026AI Engineer
Summary
This post introduces Orbit, Flywire's internal platform for integrating AI model steps into deterministic engineering workflows. Orbit allows AI-driven tasks to be defined in YAML, subjected to standard code review, and executed on existing infrastructure. Key technical contributions include the separation of orchestration, execution, and session state; implementation of timeouts, rate limits, and locks; per-step restrictions on network access, tools, and skills; and the use of structured outputs to drive workflow branches. The platform supports a range of engineering use cases, with a focus on predictable work staying in code and AI providing judgment, while human review remains integral.
More from the Agentic Workflows trail
- Reliable, Smart Workflows for Finance, Wealth and Insurance — Karthic Rao, Perpetual
- Just-in-Time Ontologies: What Cheap Intelligence Means for Data — Hrishi Olickel, Southbridge AI
- Please… Enough with the Sloppy, One-Shot SaaS Replacements — Mahmoud Abdelwahab, Railway
- We Let Our Financial Planners Write the Agents — Matthew Ragone, Range