Shopify CTO unpacks AI-native engineering at scale
Shopify CTO Mikhail Parakhin joins the Latent Space podcast to detail how Shopify reached company-wide AI adoption, what broke in the software delivery pipeline as a result, and the internal tools — Tangle, Tangent, and SimGym — built to handle it.
Score breakdown
Watch this episode to understand how a large engineering organization is redesigning its entire software delivery pipeline — not just its code generation step — to keep pace with AI-speed development.
- 01Shopify CTO Mikhail Parakhin appeared on the Latent Space podcast hosted by swyx.
- 02A December 2025 model quality inflection point drove near-universal daily AI tool usage at Shopify.
- 03Parakhin identifies PR review, CI/CD, and deployment stability — not code generation — as the real bottleneck in AI coding.
In this Latent Space episode, Shopify CTO Mikhail Parakhin describes a company that has moved well past surface-level AI integration. He points to a December 2025 inflection point when model quality shifted enough to change behavior across the organization, ultimately driving nearly everyone at Shopify to use AI tools on a daily basis. Rather than celebrating raw throughput, Parakhin stresses that token budgets only matter when paired with strong critique and review loops — and that the anti-pattern is spinning up too many parallel agents that don't communicate with each other, which he says burns tokens inefficiently compared to fewer, well-coordinated agents with a dedicated critique step.
Tangle is described as a reproducible workflow system for ML and data experimentation.
The episode goes deep on Shopify's internal tooling. Tangle is described as a reproducible workflow system for ML and data experimentation. Tangent builds on that with auto-research loops that keep iterating toward better results across pipelines, prompts, throughput, and infrastructure — a capability Parakhin says is democratizing ML experimentation beyond dedicated researchers. SimGym simulates customers using Shopify's historical merchant data and browser-based agents, with Parakhin noting that this kind of simulation is difficult to replicate without years of real merchant behavior. The episode also touches on Liquid AI for ultra-low-latency and long-context workloads, the UCP product catalog as runtime infrastructure for agents, and Shopify's approach to PR review and CI/CD in an era where code generation has outpaced the rest of the software delivery pipeline.
Key facts
- 01Shopify CTO Mikhail Parakhin appeared on the Latent Space podcast hosted by swyx.
- 02A December 2025 model quality inflection point drove near-universal daily AI tool usage at Shopify.
- 03Parakhin identifies PR review, CI/CD, and deployment stability — not code generation — as the real bottleneck in AI coding.
- 04He warns that more AI-written code can still mean more bugs in production.
- 05Running too many parallel agents that don't communicate is described as an anti-pattern that burns tokens inefficiently.
- 06A critique loop where one agent's output is reviewed by a second, ideally different, model is said to produce significantly higher-quality code.
- 07Shopify's internal AI stack includes Tangle (reproducible ML/data workflows), Tangent (auto-research loops), SimGym (customer simulation), and Liquid AI (low-latency and long-context workloads).