# Shopify Engineering

Stories and resources from the teams who build and scale Shopify, the leading cloud-based, multi-channel commerce platform.

This is one page of public article previews, not the complete archive. Follow Next page to continue. Summaries are not the original full articles.

## Building secure mobile apps in the agentic era

DevFeed: [Building secure mobile apps in the agentic era](<https://devfeed.tech/articles/building-secure-mobile-apps-in-the-agentic-era-142392.md>)

Original publisher: [Read original article](<https://shopify.engineering/secure-agentic-apps>)

Author: Michael Hughes

Published: 2026-11-18T20:34:30Z

Content type: article

Language: en

Sources: [Shopify Engineering](<https://devfeed.tech/sources/shopify-engineering.md>), [Shopify Engineering - Shopify Engineering](<https://devfeed.tech/sources/shopify-engineering-shopify-engineering.md>)

Topics: [Application Security](<https://devfeed.tech/topics/application-security.md>), [Security](<https://devfeed.tech/topics/security.md>), [Mobile](<https://devfeed.tech/topics/mobile.md>), [Android Security](<https://devfeed.tech/topics/android-security.md>)

Tags: [agentic](<https://devfeed.tech/tags/agentic.md>), [ai](<https://devfeed.tech/tags/ai.md>), [apps](<https://devfeed.tech/tags/apps.md>), [attack-surface](<https://devfeed.tech/tags/attack-surface.md>), [best-practices](<https://devfeed.tech/tags/best-practices.md>), [code](<https://devfeed.tech/tags/code.md>), [maps](<https://devfeed.tech/tags/maps.md>), [mobile](<https://devfeed.tech/tags/mobile.md>), [mobile-apps](<https://devfeed.tech/tags/mobile-apps.md>), [reviews](<https://devfeed.tech/tags/reviews.md>), [security](<https://devfeed.tech/tags/security.md>), [vulnerability](<https://devfeed.tech/tags/vulnerability.md>)

### AI overview

Shopify says its mobile app code output rose about 11x year over year, so it built a security process around a maintained map of each app's sensitive surfaces. Surface-specific skills, based on OWASP MASVS/MASTG and lessons from reported vulnerabilities, inventory items such as deep links, WebViews, stored data and dependencies, then guide focused reviews of one item at a time. Weekday reviews compare inventories with the last accepted map, examine changed items using read-only tools, run a second pass for uncovered security-relevant changes, validate findings, and publish a change summary. Agents also check security news against the apps and use the same mapping process to assess third-party libraries. These checks complement Dispatch, which finds and proves vulnerabilities in changed code; the map tracks broader app surfaces and practices. Fixed vulnerabilities inform future checks.

### Source excerpt

How we scale our security with attack surface maps, focused AI reviews, and checks that improve with every vulnerability fixed.

## Cyber Chaos Monkey: Staying ahead of security threats with AI agents

DevFeed: [Cyber Chaos Monkey: Staying ahead of security threats with AI agents](<https://devfeed.tech/articles/cyber-chaos-monkey-staying-ahead-of-security-threats-with-ai-agents-130858.md>)

Original publisher: [Read original article](<https://shopify.engineering/cyber-chaos-monkey>)

Author: Dan Scofield

Published: 2026-11-12T14:57:16Z

Content type: article

Language: en

Sources: [Shopify Engineering](<https://devfeed.tech/sources/shopify-engineering.md>), [Shopify Engineering - Shopify Engineering](<https://devfeed.tech/sources/shopify-engineering-shopify-engineering.md>)

Topics: [AI in cybersecurity](<https://devfeed.tech/topics/ai-in-cybersecurity.md>), [ai security](<https://devfeed.tech/topics/ai-security.md>), [Multi Agent Systems](<https://devfeed.tech/topics/multi-agent-systems.md>), [Production Engineering](<https://devfeed.tech/topics/production-engineering.md>), [Chaos Engineering](<https://devfeed.tech/topics/chaos-engineering.md>)

Tags: [2](<https://devfeed.tech/tags/2.md>), [2026](<https://devfeed.tech/tags/2026.md>), [3](<https://devfeed.tech/tags/3.md>), [about](<https://devfeed.tech/tags/about.md>), [agents](<https://devfeed.tech/tags/agents.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-agents](<https://devfeed.tech/tags/ai-agents.md>), [bugs](<https://devfeed.tech/tags/bugs.md>), [chaos](<https://devfeed.tech/tags/chaos.md>), [cyber](<https://devfeed.tech/tags/cyber.md>), [infrastructure](<https://devfeed.tech/tags/infrastructure.md>), [knowledge](<https://devfeed.tech/tags/knowledge.md>), [monkey](<https://devfeed.tech/tags/monkey.md>), [production](<https://devfeed.tech/tags/production.md>), [production-infrastructure](<https://devfeed.tech/tags/production-infrastructure.md>), [risks](<https://devfeed.tech/tags/risks.md>), [security](<https://devfeed.tech/tags/security.md>), [shopify](<https://devfeed.tech/tags/shopify.md>), [systems](<https://devfeed.tech/tags/systems.md>), [with](<https://devfeed.tech/tags/with.md>)

### AI overview

Shopify's Cyber Chaos Monkey (CCM) uses AI agents to probe live production systems with test shops and organizations, aiming to find vulnerabilities before attackers do. Its Discovery component uses system knowledge and cyber models to identify leads; Sandbox agents test them with live requests, production logs, and source code, then report findings for further investigation. Shopify says the system has run tens of thousands of engagements and acted on dozens of impactful findings without causing an outage or incident. Safety measures include containerized, least-privilege jobs; ephemeral credentials managed through a proxy; restricted egress; and Rules of Engagement. A separately prompted judge agent reviews the executor's session in real time and kills it if it detects prohibited behavior. The run also terminates if the judge or executor fails, using pod-local orchestration and heartbeats. Shopify presents its knowledge of its own systems as an advantage; the account does not provide independent evaluation of CCM's effectiveness.

### Source excerpt

How we pair AI agents with our knowledge of Shopify's systems to safely attack our production infrastructure, find bugs, and reduce risks.

## How we rebuilt the Shopify app in 12 weeks

DevFeed: [How we rebuilt the Shopify app in 12 weeks](<https://devfeed.tech/articles/how-we-rebuilt-the-shopify-app-in-12-weeks-126837.md>)

Original publisher: [Read original article](<https://shopify.engineering/shopify-app-rebuild>)

Author: Remi Vanhee

Published: 2026-11-10T14:36:23Z

Content type: article

Language: en

Sources: [Shopify Engineering](<https://devfeed.tech/sources/shopify-engineering.md>), [Shopify Engineering - Shopify Engineering](<https://devfeed.tech/sources/shopify-engineering-shopify-engineering.md>)

Topics: [AI-assisted coding](<https://devfeed.tech/topics/ai-assisted-coding.md>), [software-architecture](<https://devfeed.tech/topics/software-architecture.md>), [CI/CD](<https://devfeed.tech/topics/cicd.md>), [mobile-app-performance](<https://devfeed.tech/topics/mobile-app-performance.md>), [engineering-culture](<https://devfeed.tech/topics/engineering-culture.md>), [Integration testing](<https://devfeed.tech/topics/integration-testing.md>), [context-architecture](<https://devfeed.tech/topics/context-architecture.md>), [Shopify](<https://devfeed.tech/topics/shopify.md>), [Android](<https://devfeed.tech/topics/android.md>), [android-app-bundle](<https://devfeed.tech/topics/android-app-bundle.md>), [app startup](<https://devfeed.tech/topics/app-startup.md>)

Tags: [agents](<https://devfeed.tech/tags/agents.md>), [app](<https://devfeed.tech/tags/app.md>), [architecture](<https://devfeed.tech/tags/architecture.md>), [code](<https://devfeed.tech/tags/code.md>), [code-review](<https://devfeed.tech/tags/code-review.md>), [mobile](<https://devfeed.tech/tags/mobile.md>), [shopify](<https://devfeed.tech/tags/shopify.md>), [tooling](<https://devfeed.tech/tags/tooling.md>), [validation](<https://devfeed.tech/tags/validation.md>), [workflow](<https://devfeed.tech/tags/workflow.md>)

### AI overview

Shopify says it rebuilt its mobile app from React Native to native Swift and Kotlin in 12 weeks with about 30 engineers and agents writing most of the code. The central change was the workflow around implementation: a shared cross-platform Reflex architecture, a CLI and testable business logic for millisecond feedback without a device, small migration checkpoints checked against the existing app, and CI guardrails for architectural drift. Pods of two engineers owned product areas across both platforms; agents reviewed PRs first, while humans retained final review and shipping decisions. Consistency made cross-platform changes easier to compare and reuse, at the cost of some platform idiom. Faster code generation shifted constraints to compute, CI, review, merging, and coordination. Shopify reports launch-time reductions, smaller Android binaries and lower memory use, and improved Android crash-free sessions; the excerpt provides figures for these outcomes. It also says new features without an existing screen remain a distinct challenge.

### Source excerpt

What changed when agents started writing our mobile code, and how we redesigned our architecture, tooling, and workflow around validation.

## Reflex: an architecture for building mobile apps with agents

DevFeed: [Reflex: an architecture for building mobile apps with agents](<https://devfeed.tech/articles/reflex-an-architecture-for-building-mobile-apps-with-agents-119294.md>)

Original publisher: [Read original article](<https://shopify.engineering/reflex>)

Author: Thiago Magalhaes

Published: 2026-11-05T15:41:40Z

Content type: article

Language: en

Sources: [Shopify Engineering](<https://devfeed.tech/sources/shopify-engineering.md>), [Shopify Engineering - Shopify Engineering](<https://devfeed.tech/sources/shopify-engineering-shopify-engineering.md>)

Topics: [Mobile](<https://devfeed.tech/topics/mobile.md>), [mobile devops](<https://devfeed.tech/topics/mobile-devops.md>), [Android](<https://devfeed.tech/topics/android.md>), [iOS](<https://devfeed.tech/topics/ios.md>), [Swift](<https://devfeed.tech/topics/swift.md>), [SwiftUI](<https://devfeed.tech/topics/swiftui.md>)

Tags: [abstraction](<https://devfeed.tech/tags/abstraction.md>), [access-control](<https://devfeed.tech/tags/access-control.md>), [accessibility](<https://devfeed.tech/tags/accessibility.md>), [actions](<https://devfeed.tech/tags/actions.md>), [agent](<https://devfeed.tech/tags/agent.md>), [agentic](<https://devfeed.tech/tags/agentic.md>), [agents](<https://devfeed.tech/tags/agents.md>), [ai](<https://devfeed.tech/tags/ai.md>), [android](<https://devfeed.tech/tags/android.md>), [app](<https://devfeed.tech/tags/app.md>), [apps](<https://devfeed.tech/tags/apps.md>), [architecture](<https://devfeed.tech/tags/architecture.md>), [behavior](<https://devfeed.tech/tags/behavior.md>), [emulator](<https://devfeed.tech/tags/emulator.md>), [ios](<https://devfeed.tech/tags/ios.md>), [mobile](<https://devfeed.tech/tags/mobile.md>), [mobile-app](<https://devfeed.tech/tags/mobile-app.md>), [reflex](<https://devfeed.tech/tags/reflex.md>), [sync](<https://devfeed.tech/tags/sync.md>), [test](<https://devfeed.tech/tags/test.md>)

### AI overview

Reflex lets Shopify test and drive native iOS and Android app behavior without rendering UI: platform logic runs in a UI-free core, and each screen exposes JSON state and actions through a consistent ViewModel contract. A CLI uses that contract for exploration and behavior tests; one test suite runs against both implementations, enforcing parity while keeping platform code separate. Tests use real app logic and fixtures at external boundaries, with network access blocked to keep runs deterministic. Shopify reports 1,700+ behavior tests finishing in about four minutes on CI, and an example test running in a few hundred milliseconds on both platforms versus about two seconds on an iOS simulator. These tests cover behavior rather than pixels, so the described workflow also uses visual review, screenshot tests for selected components, and live integration journeys. The article presents the architecture and implementation steps, not a transferable library.

### Source excerpt

Our architecture lets agents test mobile app behavior without an emulator and use one test suite to keep iOS and Android in sync.

## We gave AI agents a mobile dev environment

DevFeed: [We gave AI agents a mobile dev environment](<https://devfeed.tech/articles/we-gave-ai-agents-a-mobile-dev-environment-95739.md>)

Original publisher: [Read original article](<https://shopify.engineering/remote-dev>)

Author: Michael Garfinkle

Published: 2026-10-22T12:56:38Z

Content type: article

Language: en

Sources: [Shopify Engineering](<https://devfeed.tech/sources/shopify-engineering.md>), [Shopify Engineering - Shopify Engineering](<https://devfeed.tech/sources/shopify-engineering-shopify-engineering.md>)

Topics: [AI-assisted coding](<https://devfeed.tech/topics/ai-assisted-coding.md>), [agentic workflows](<https://devfeed.tech/topics/agentic-workflows.md>), [Multi Agent Systems](<https://devfeed.tech/topics/multi-agent-systems.md>), [mobile devops](<https://devfeed.tech/topics/mobile-devops.md>), [Developer experience](<https://devfeed.tech/topics/developer-experience.md>), [CI/CD](<https://devfeed.tech/topics/cicd.md>)

Tags: [3d](<https://devfeed.tech/tags/3d.md>), [agentic-workflows](<https://devfeed.tech/tags/agentic-workflows.md>), [agents](<https://devfeed.tech/tags/agents.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-agents](<https://devfeed.tech/tags/ai-agents.md>), [android](<https://devfeed.tech/tags/android.md>), [android-studio](<https://devfeed.tech/tags/android-studio.md>), [android-vm](<https://devfeed.tech/tags/android-vm.md>), [animations](<https://devfeed.tech/tags/animations.md>), [apps](<https://devfeed.tech/tags/apps.md>), [build](<https://devfeed.tech/tags/build.md>), [dev](<https://devfeed.tech/tags/dev.md>), [developers](<https://devfeed.tech/tags/developers.md>), [environment](<https://devfeed.tech/tags/environment.md>), [laptops](<https://devfeed.tech/tags/laptops.md>), [mobile](<https://devfeed.tech/tags/mobile.md>), [mobile-dev](<https://devfeed.tech/tags/mobile-dev.md>), [parallel](<https://devfeed.tech/tags/parallel.md>), [remote](<https://devfeed.tech/tags/remote.md>), [test](<https://devfeed.tech/tags/test.md>)

### AI overview

Remote Dev gives each River agent a separate remote environment so mobile builds and tests can run in parallel without tying up developers' laptops. A pool of warm Macs runs iOS builds and tools; Android emulators run on separate Linux VMs because macOS does not support the nested virtualization they require. Agents connect over SSH, and a CLI plus observable tmux panes help them run tasks and report progress. Prebuilt apps, warm caches, and prepared machines cut the wait from a request to inspecting a running app from over 30 minutes to a few minutes. River can build, test, interact with iOS and Android apps, capture evidence, and create PRs. Live Preview streams a running simulator or emulator to a browser over WebSockets for shared, interactive testing without local setup. The article reports River's share of merged mobile PRs rising from 6% to 61% over time; it does not establish that Remote Dev alone caused the increase.

### Source excerpt

We built Remote Dev so AI agents can build and test apps in parallel, without maxing out developers' laptops.

## How Shopify turns open models into task experts

DevFeed: [How Shopify turns open models into task experts](<https://devfeed.tech/articles/how-shopify-turns-open-models-into-task-experts-91330.md>)

Original publisher: [Read original article](<https://shopify.engineering/open-model-task-experts>)

Author: Andrew McNamara

Published: 2026-10-21T02:12:40Z

Content type: article

Language: en

Sources: [Shopify Engineering](<https://devfeed.tech/sources/shopify-engineering.md>), [Shopify Engineering - Shopify Engineering](<https://devfeed.tech/sources/shopify-engineering-shopify-engineering.md>)

Topics: [LLM optimization](<https://devfeed.tech/topics/llm-optimization.md>), [Fine-tuning](<https://devfeed.tech/topics/fine-tuning.md>), [Nemotron](<https://devfeed.tech/topics/nemotron.md>), [Open Source Models & Datasets](<https://devfeed.tech/topics/open-source-models-datasets.md>), [Frontier AI](<https://devfeed.tech/topics/frontier-ai.md>), [AI Chat](<https://devfeed.tech/topics/ai-chat.md>), [Mixture of Experts (MoE)](<https://devfeed.tech/topics/mixture-of-experts-moe.md>), [TensorRT](<https://devfeed.tech/topics/tensorrt.md>), [Shopify](<https://devfeed.tech/topics/shopify.md>)

Tags: [2026](<https://devfeed.tech/tags/2026.md>), [3](<https://devfeed.tech/tags/3.md>), [ace](<https://devfeed.tech/tags/ace.md>), [added](<https://devfeed.tech/tags/added.md>), [build](<https://devfeed.tech/tags/build.md>), [experts](<https://devfeed.tech/tags/experts.md>), [faster](<https://devfeed.tech/tags/faster.md>), [frontier](<https://devfeed.tech/tags/frontier.md>), [frontier-model](<https://devfeed.tech/tags/frontier-model.md>), [gpus](<https://devfeed.tech/tags/gpus.md>), [model](<https://devfeed.tech/tags/model.md>), [models](<https://devfeed.tech/tags/models.md>), [nvidia](<https://devfeed.tech/tags/nvidia.md>), [open](<https://devfeed.tech/tags/open.md>), [post](<https://devfeed.tech/tags/post.md>), [shopify](<https://devfeed.tech/tags/shopify.md>), [software](<https://devfeed.tech/tags/software.md>), [token](<https://devfeed.tech/tags/token.md>), [trains](<https://devfeed.tech/tags/trains.md>), [work](<https://devfeed.tech/tags/work.md>)

### AI overview

Shopify's Sidekick keeps a frontier model for merchant interaction and planning, while open-model subagents handle focused, token-heavy tasks. For GraphQL, Shopify post-trained NVIDIA Nemotron 3.5 Lightning through a loop that scores quality with a judge calibrated to human labels, improves the frontier-agent baseline, benchmarks open models and serving stacks, turns failed production conversations into training examples, and retrains on NVIDIA hardware. Across six loops, the model's GraphQL score rose from 37.7 to 74.5, versus 73 for the frontier model. In production-traffic replay, it returned responses at a 0.87-second median versus 6.50 seconds for the frontier API, with the slowest 1% finishing 8x sooner and serving costing about 90% less. Self-healing repaired 69% of attempted failures across 86 nightly runs. Tool results varied by workload: TensorRT-LLM did the most work per GPU for Buyer Profile; NVIDIA measured SimGym 4.5x faster on B200 than H200 at 1.48x lower cost. An Analytics training job ran 1.86x faster on eight B300s than eight H200s, using 46% fewer GPU-hours.

### Source excerpt

Sidekick's frontier model hands its most token-heavy work to open models that Shopify post-trains and serves itself. Here's the loop we use to build them, and where NVIDIA's models, software, and GPUs make each turn faster and cheaper.

## Cross-store product clustering across millions of stores

DevFeed: [Cross-store product clustering across millions of stores](<https://devfeed.tech/articles/cross-store-product-clustering-across-millions-of-stores-90670.md>)

Original publisher: [Read original article](<https://shopify.engineering/catalog-clustering-part-ii>)

Author: Ilia Kuchumov

Published: 2026-10-20T13:48:59Z

Content type: article

Language: en

Sources: [Shopify Engineering](<https://devfeed.tech/sources/shopify-engineering.md>), [Shopify Engineering - Shopify Engineering](<https://devfeed.tech/sources/shopify-engineering-shopify-engineering.md>)

Topics: [Entity resolution](<https://devfeed.tech/topics/entity-resolution.md>), [clustering](<https://devfeed.tech/topics/clustering.md>), [resource orchestration](<https://devfeed.tech/topics/resource-orchestration.md>), [AI Models](<https://devfeed.tech/topics/ai-models.md>), [product mindset](<https://devfeed.tech/topics/product-mindset.md>), [distributed-training](<https://devfeed.tech/topics/distributed-training.md>)

Tags: [ai](<https://devfeed.tech/tags/ai.md>), [algorithm](<https://devfeed.tech/tags/algorithm.md>), [api](<https://devfeed.tech/tags/api.md>), [approximate-nearest-neighbor](<https://devfeed.tech/tags/approximate-nearest-neighbor.md>), [approximate-nearest-neighbor-search](<https://devfeed.tech/tags/approximate-nearest-neighbor-search.md>), [based](<https://devfeed.tech/tags/based.md>), [cluster](<https://devfeed.tech/tags/cluster.md>), [clustering](<https://devfeed.tech/tags/clustering.md>), [clusters](<https://devfeed.tech/tags/clusters.md>), [graph](<https://devfeed.tech/tags/graph.md>), [has](<https://devfeed.tech/tags/has.md>), [matching](<https://devfeed.tech/tags/matching.md>), [partitioning](<https://devfeed.tech/tags/partitioning.md>)

### AI overview

Shopify describes a system that matches product listings across merchants and groups likely matches under a unified product identifier. It combines approximate-neighbor candidate retrieval, tiered matching models, graph partitioning, and learned merge decisions, while prioritizing precision and refreshing clusters as listings change.

### Source excerpt

How we group product listings across millions of stores using tiered matching models, graph partitioning, and learned cluster merge decisions.

## Building Overexposed: understanding application exposure

DevFeed: [Building Overexposed: understanding application exposure](<https://devfeed.tech/articles/building-overexposed-understanding-application-exposure-90443.md>)

Original publisher: [Read original article](<https://shopify.engineering/overexposed>)

Author: Simar Singh

Published: 2026-10-19T21:54:14Z

Content type: article

Language: en

Sources: [Shopify Engineering](<https://devfeed.tech/sources/shopify-engineering.md>), [Shopify Engineering - Shopify Engineering](<https://devfeed.tech/sources/shopify-engineering-shopify-engineering.md>)

Topics: [Exposure Management](<https://devfeed.tech/topics/exposure-management.md>), [CI/CD](<https://devfeed.tech/topics/cicd.md>), [GitHub](<https://devfeed.tech/topics/github.md>), [aws inspector](<https://devfeed.tech/topics/aws-inspector.md>), [Cloud Networking](<https://devfeed.tech/topics/cloud-networking.md>), [identity-aware proxy](<https://devfeed.tech/topics/identity-aware-proxy.md>), [Load Balancing](<https://devfeed.tech/topics/load-balancing.md>)

Tags: [access-control](<https://devfeed.tech/tags/access-control.md>), [api](<https://devfeed.tech/tags/api.md>), [authentication](<https://devfeed.tech/tags/authentication.md>), [build](<https://devfeed.tech/tags/build.md>), [code-review](<https://devfeed.tech/tags/code-review.md>), [coding-agents](<https://devfeed.tech/tags/coding-agents.md>), [credentials](<https://devfeed.tech/tags/credentials.md>), [dns](<https://devfeed.tech/tags/dns.md>), [it](<https://devfeed.tech/tags/it.md>), [scanner](<https://devfeed.tech/tags/scanner.md>)

### AI overview

Shopify describes Overexposed, a scanner that inventories GKE Ingresses and Cloud Run services, probes endpoints anonymously, and classifies their exposure using access policies and an allowlist. The article details protections against server-side request forgery, evidence-based verdicts, and testing changes against saved results. It also discusses using AI coding agents and code review, mutation testing, and canary targets to improve the scanner's tests.

### Source excerpt

Our first scanner read config files and missed what was running. We rebuilt it with the cloud inventory, a careful probe, and honest results.

## ShopGym: Realistic, reproducible sandboxes for shopping agents

DevFeed: [ShopGym: Realistic, reproducible sandboxes for shopping agents](<https://devfeed.tech/articles/shopgym-realistic-reproducible-sandboxes-for-shopping-agents-63600.md>)

Original publisher: [Read original article](<https://shopify.engineering/shopgym>)

Author: Mingyu Zhao

Published: 2026-10-01T16:23:24Z

Content type: article

Language: en

Sources: [Shopify Engineering](<https://devfeed.tech/sources/shopify-engineering.md>), [Shopify Engineering - Shopify Engineering](<https://devfeed.tech/sources/shopify-engineering-shopify-engineering.md>)

Topics: [reproducibility](<https://devfeed.tech/topics/reproducibility.md>), [gui-agents](<https://devfeed.tech/topics/gui-agents.md>)

Tags: [agents](<https://devfeed.tech/tags/agents.md>), [benchmark](<https://devfeed.tech/tags/benchmark.md>), [evaluation](<https://devfeed.tech/tags/evaluation.md>), [sandboxes](<https://devfeed.tech/tags/sandboxes.md>)

### AI overview

ShopGym turns live storefronts into resettable sandbox shops and generates shopping tasks for testing shopping agents. Across 224 tasks in six shops, its synthetic stores preserved key structural properties of live stores, and agent performance on synthetic shops correlated positively with performance on their live counterparts. The evaluation also found gaps on some focused tasks, so the sandbox shops did not reproduce live-store difficulty exactly.

### Source excerpt

ShopGym creates realistic online stores and generates shopping tasks based on each store's products and features. Developers can then repeatedly test shopping agents under consistent conditions.

## Helix: The internal tool powering our Shopify app's native migration

DevFeed: [Helix: The internal tool powering our Shopify app's native migration](<https://devfeed.tech/articles/helix-the-internal-tool-powering-our-shopify-app-s-native-migration-57640.md>)

Original publisher: [Read original article](<https://shopify.engineering/helix>)

Author: Talha Naqvi

Published: 2026-09-21T21:12:33Z

Content type: article

Language: en

Sources: [Shopify Engineering](<https://devfeed.tech/sources/shopify-engineering.md>), [Shopify Engineering - Shopify Engineering](<https://devfeed.tech/sources/shopify-engineering-shopify-engineering.md>)

Topics: [migration](<https://devfeed.tech/topics/migration.md>), [Large Language Model](<https://devfeed.tech/topics/llm.md>), [Mobile](<https://devfeed.tech/topics/mobile.md>), [React Native](<https://devfeed.tech/topics/react-native.md>), [Kotlin](<https://devfeed.tech/topics/kotlin.md>), [Swift](<https://devfeed.tech/topics/swift.md>), [Code](<https://devfeed.tech/topics/code.md>), [Shopify](<https://devfeed.tech/topics/shopify.md>)

Tags: [architecture](<https://devfeed.tech/tags/architecture.md>), [code-reviews](<https://devfeed.tech/tags/code-reviews.md>), [kotlin](<https://devfeed.tech/tags/kotlin.md>), [llms](<https://devfeed.tech/tags/llms.md>), [migration](<https://devfeed.tech/tags/migration.md>), [mobile-apps](<https://devfeed.tech/tags/mobile-apps.md>), [quality-gates](<https://devfeed.tech/tags/quality-gates.md>), [swift](<https://devfeed.tech/tags/swift.md>)

### AI overview

Shopify describes Helix, an internal tool that uses LLMs, small checkpoints, tests, visual review, and strict code-review gates to migrate screens from React Native to native Swift and Kotlin.

### Source excerpt

We built Helix to help LLMs rebuild the Shopify app in Swift and Kotlin, using small checkpoints and strict quality gates to keep the code shippable.

## Migrating Shop app from React Native to native

DevFeed: [Migrating Shop app from React Native to native](<https://devfeed.tech/articles/migrating-shop-app-from-react-native-to-native-1583.md>)

Original publisher: [Read original article](<https://shopify.engineering/shop-app-migration>)

Author: Max Da Silva

Published: 2026-09-10T12:27:06Z

Content type: article

Language: en

Sources: [Shopify Engineering](<https://devfeed.tech/sources/shopify-engineering.md>), [Shopify Engineering - Shopify Engineering](<https://devfeed.tech/sources/shopify-engineering-shopify-engineering.md>)

Topics: [migration](<https://devfeed.tech/topics/migration.md>)

Tags: [agents](<https://devfeed.tech/tags/agents.md>), [ai](<https://devfeed.tech/tags/ai.md>), [android](<https://devfeed.tech/tags/android.md>), [compose](<https://devfeed.tech/tags/compose.md>), [ios](<https://devfeed.tech/tags/ios.md>), [kotlin](<https://devfeed.tech/tags/kotlin.md>), [migration](<https://devfeed.tech/tags/migration.md>), [react-native](<https://devfeed.tech/tags/react-native.md>), [swift](<https://devfeed.tech/tags/swift.md>)

### AI overview

Shopify describes migrating the Shop app from React Native to native Swift and Kotlin development. Coding agents supported a proof of concept and the subsequent rebuild while the team aimed to preserve feature behavior and analytics events.

### Source excerpt

We migrated the Shop app from React Native to Swift and Kotlin. Assisted by AI, the team was able to go from a proof of concept to a fully rebuilt native app published in the app stores in just 12 weeks.

## Native is now the future of mobile at Shopify

DevFeed: [Native is now the future of mobile at Shopify](<https://devfeed.tech/articles/native-is-now-the-future-of-mobile-at-shopify-1302.md>)

Original publisher: [Read original article](<https://shopify.engineering/back-to-native>)

Author: Mustafa Ali

Published: 2026-09-10T12:25:28Z

Content type: article

Language: en

Sources: [Shopify Engineering](<https://devfeed.tech/sources/shopify-engineering.md>), [Shopify Engineering - Shopify Engineering](<https://devfeed.tech/sources/shopify-engineering-shopify-engineering.md>)

Topics: [React Native](<https://devfeed.tech/topics/react-native.md>), [AI-assisted coding](<https://devfeed.tech/topics/ai-assisted-coding.md>), [Large Language Model](<https://devfeed.tech/topics/llm.md>), [iOS](<https://devfeed.tech/topics/ios.md>)

Tags: [agents](<https://devfeed.tech/tags/agents.md>), [android](<https://devfeed.tech/tags/android.md>), [apps](<https://devfeed.tech/tags/apps.md>), [coding](<https://devfeed.tech/tags/coding.md>), [kotlin](<https://devfeed.tech/tags/kotlin.md>), [llms](<https://devfeed.tech/tags/llms.md>), [mobile](<https://devfeed.tech/tags/mobile.md>), [models](<https://devfeed.tech/tags/models.md>), [react-native](<https://devfeed.tech/tags/react-native.md>), [shopify](<https://devfeed.tech/tags/shopify.md>), [swift](<https://devfeed.tech/tags/swift.md>)

### AI overview

Shopify is moving from React Native back to native Swift and Kotlin development after finding that coding agents and LLMs reduce the cost of implementing mobile features separately on each platform.

### Source excerpt

Coding agents changed what it costs to build mobile apps twice. Here's why Shopify is moving from React Native back to Swift and Kotlin.

## How River takes security work from a fix to merge

DevFeed: [How River takes security work from a fix to merge](<https://devfeed.tech/articles/how-river-takes-security-work-from-a-fix-to-merge-1554.md>)

Original publisher: [Read original article](<https://shopify.engineering/river-vulnerability-remediation>)

Author: Erin Son

Published: 2026-09-02T16:30:45Z

Content type: article

Language: en

Sources: [Shopify Engineering](<https://devfeed.tech/sources/shopify-engineering.md>), [Shopify Engineering - Shopify Engineering](<https://devfeed.tech/sources/shopify-engineering-shopify-engineering.md>)

Topics: [Vulnerabilities](<https://devfeed.tech/topics/vulnerabilities.md>), [AI Bots](<https://devfeed.tech/topics/ai-bots.md>)

Tags: [agentic](<https://devfeed.tech/tags/agentic.md>), [ai-agent](<https://devfeed.tech/tags/ai-agent.md>), [autonomous](<https://devfeed.tech/tags/autonomous.md>), [ci](<https://devfeed.tech/tags/ci.md>), [security](<https://devfeed.tech/tags/security.md>), [shopify](<https://devfeed.tech/tags/shopify.md>), [slack](<https://devfeed.tech/tags/slack.md>), [vulnerability](<https://devfeed.tech/tags/vulnerability.md>), [workflow](<https://devfeed.tech/tags/workflow.md>)

### AI overview

Shopify describes River, an AI agent that manages vulnerability remediation from patch review through merge and verification against the repository head and dependency graph. The article reports a 70% reduction in open dependency issues during the workflow's first 11 days.

### Source excerpt

River, Shopify's AI agent in Slack, enables autonomous vulnerability remediation, not just detection.

## Gisting: Compressing LLM Agent context to ↑ throughput and ↓ cost

DevFeed: [Gisting: Compressing LLM Agent context to ↑ throughput and ↓ cost](<https://devfeed.tech/articles/gisting-compressing-llm-agent-context-to-throughput-and-cost-1403.md>)

Original publisher: [Read original article](<https://shopify.engineering/gisting>)

Author: Cody Mazza-Anthony

Published: 2026-08-19T14:32:58Z

Content type: article

Language: en

Sources: [Shopify Engineering](<https://devfeed.tech/sources/shopify-engineering.md>), [Shopify Engineering - Shopify Engineering](<https://devfeed.tech/sources/shopify-engineering-shopify-engineering.md>)

Topics: [Compression](<https://devfeed.tech/topics/compression.md>), [Large Language Model](<https://devfeed.tech/topics/llm.md>), [Embeddings](<https://devfeed.tech/topics/embeddings.md>), [Latency](<https://devfeed.tech/topics/latency.md>), [Inference](<https://devfeed.tech/topics/inference.md>), [Post-training optimization](<https://devfeed.tech/topics/post-training-optimization.md>), [GraphQL](<https://devfeed.tech/topics/graphql.md>), [model-deployment](<https://devfeed.tech/topics/model-deployment.md>)

Tags: [compression](<https://devfeed.tech/tags/compression.md>), [embedding](<https://devfeed.tech/tags/embedding.md>), [inference](<https://devfeed.tech/tags/inference.md>), [latency](<https://devfeed.tech/tags/latency.md>), [llm](<https://devfeed.tech/tags/llm.md>), [model](<https://devfeed.tech/tags/model.md>), [tokens](<https://devfeed.tech/tags/tokens.md>)

### AI overview

Gisting compresses an LLM agent's system prompt into learned gist tokens, preserving prediction quality while reducing inference latency, increasing throughput, and lowering GPU requirements.

### Source excerpt

Gisting compresses context into a set of learned tokens, preserving its quality while making the model faster and cheaper.

## How we raised mobile end-to-end test stability to 98%

DevFeed: [How we raised mobile end-to-end test stability to 98%](<https://devfeed.tech/articles/how-we-raised-mobile-end-to-end-test-stability-to-98-1496.md>)

Original publisher: [Read original article](<https://shopify.engineering/mobile-e2e-testing>)

Author: Michael Garfinkle

Published: 2026-08-12T20:02:35Z

Content type: article

Language: en

Sources: [Shopify Engineering](<https://devfeed.tech/sources/shopify-engineering.md>), [Shopify Engineering - Shopify Engineering](<https://devfeed.tech/sources/shopify-engineering-shopify-engineering.md>)

Topics: [Continuous integration](<https://devfeed.tech/topics/continuous-integration.md>), [React Native](<https://devfeed.tech/topics/react-native.md>), [App](<https://devfeed.tech/topics/app.md>), [Pull Request](<https://devfeed.tech/topics/pull-request.md>), [User Experience](<https://devfeed.tech/topics/user-experience.md>)

Tags: [app](<https://devfeed.tech/tags/app.md>), [ci](<https://devfeed.tech/tags/ci.md>), [computer-vision](<https://devfeed.tech/tags/computer-vision.md>), [mobile](<https://devfeed.tech/tags/mobile.md>), [pull-request](<https://devfeed.tech/tags/pull-request.md>), [react-native](<https://devfeed.tech/tags/react-native.md>), [testing](<https://devfeed.tech/tags/testing.md>), [user-experience](<https://devfeed.tech/tags/user-experience.md>)

### AI overview

Shopify rebuilt its mobile end-to-end testing framework with a strict builder-style API and computer vision. The approach raised test stability from 50% to 98% and restored reliable blocking checks for pull requests.

### Source excerpt

We rebuilt our mobile end-to-end testing framework with a strict API and computer vision, raising test stability drastically.

## Sidekick's continual learning loop

DevFeed: [Sidekick's continual learning loop](<https://devfeed.tech/articles/sidekick-s-continual-learning-loop-1617.md>)

Original publisher: [Read original article](<https://shopify.engineering/sidekicks-continual-learning-loop>)

Author: Andrew McNamara

Published: 2026-08-05T14:52:54Z

Content type: article

Language: en

Sources: [Shopify Engineering](<https://devfeed.tech/sources/shopify-engineering.md>), [Shopify Engineering - Shopify Engineering](<https://devfeed.tech/sources/shopify-engineering-shopify-engineering.md>)

Topics: [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>), [Shopify](<https://devfeed.tech/topics/shopify.md>), [GraphQL](<https://devfeed.tech/topics/graphql.md>), [Ground truth / benchmark quality](<https://devfeed.tech/topics/ground-truth-benchmark-quality.md>), [Latency](<https://devfeed.tech/topics/latency.md>), [Code](<https://devfeed.tech/topics/code.md>)

Tags: [agent](<https://devfeed.tech/tags/agent.md>), [ai](<https://devfeed.tech/tags/ai.md>), [frontier-model](<https://devfeed.tech/tags/frontier-model.md>), [latency](<https://devfeed.tech/tags/latency.md>), [model](<https://devfeed.tech/tags/model.md>), [production](<https://devfeed.tech/tags/production.md>), [retrieval](<https://devfeed.tech/tags/retrieval.md>), [routing](<https://devfeed.tech/tags/routing.md>), [safety](<https://devfeed.tech/tags/safety.md>)

### AI overview

Shopify describes a continual learning loop for its GraphQL agent that turns production failures, user corrections, and sampled traffic into ground truth and model-weight improvements. The approach is reported to exceed frontier-model quality while reducing latency and serving costs by 96%.

### Source excerpt

How we compress production failures into model weights every day, beat frontier-model quality, and cut serving costs 96%.

## Building an agentic harness that outlasts the model

DevFeed: [Building an agentic harness that outlasts the model](<https://devfeed.tech/articles/building-an-agentic-harness-that-outlasts-the-model-1319.md>)

Original publisher: [Read original article](<https://shopify.engineering/building-an-agentic-harness-that-outlasts-the-model>)

Author: Zack Deveau

Published: 2026-07-29T15:30:00Z

Content type: article

Language: en

Sources: [Shopify Engineering](<https://devfeed.tech/sources/shopify-engineering.md>), [Shopify Engineering - Shopify Engineering](<https://devfeed.tech/sources/shopify-engineering-shopify-engineering.md>)

Topics: [Application Security](<https://devfeed.tech/topics/application-security.md>), [Shopify](<https://devfeed.tech/topics/shopify.md>), [Vulnerabilities](<https://devfeed.tech/topics/vulnerabilities.md>), [Code review](<https://devfeed.tech/topics/code-review.md>), [Orchestration](<https://devfeed.tech/topics/orchestration.md>), [Pull Request](<https://devfeed.tech/topics/pull-request.md>), [Ruby on Rails](<https://devfeed.tech/topics/ruby-on-rails.md>), [Ruby](<https://devfeed.tech/topics/ruby.md>), [Web app](<https://devfeed.tech/topics/webapp.md>), [Back end](<https://devfeed.tech/topics/backend.md>)

Tags: [agentic](<https://devfeed.tech/tags/agentic.md>), [application-security](<https://devfeed.tech/tags/application-security.md>), [backend](<https://devfeed.tech/tags/backend.md>), [building](<https://devfeed.tech/tags/building.md>), [code](<https://devfeed.tech/tags/code.md>), [orchestration](<https://devfeed.tech/tags/orchestration.md>), [pull-requests](<https://devfeed.tech/tags/pull-requests.md>), [review](<https://devfeed.tech/tags/review.md>), [ruby](<https://devfeed.tech/tags/ruby.md>), [shopify](<https://devfeed.tech/tags/shopify.md>), [vulnerabilities](<https://devfeed.tech/tags/vulnerabilities.md>), [web-applications](<https://devfeed.tech/tags/web-applications.md>), [workflow](<https://devfeed.tech/tags/workflow.md>)

### AI overview

Shopify describes an agentic code review and test-oracle harness for application security. The harness scans software for vulnerabilities, validates findings with real tests, generates Shopify-specific fixes, and opens relevant pull requests. The article also explains its Dispatch orchestrator, parallel scanning workflow, reusable application context, and diff-based follow-up scans.

### Source excerpt

We built an agentic code review and test oracle harness that discovers vulnerabilities, proves them with real tests, and provides Shopify-tuned fixes.

## Inside Shopify Hack Days: Building a prototype for music-playing pages

DevFeed: [Inside Shopify Hack Days: Building a prototype for music-playing pages](<https://devfeed.tech/articles/inside-shopify-hack-days-building-a-prototype-for-music-playing-pages-1406.md>)

Original publisher: [Read original article](<https://shopify.engineering/hack-days>)

Author: Justin Henricks

Published: 2026-07-14T13:55:57Z

Content type: article

Language: en

Sources: [Shopify Engineering](<https://devfeed.tech/sources/shopify-engineering.md>), [Shopify Engineering - Shopify Engineering](<https://devfeed.tech/sources/shopify-engineering-shopify-engineering.md>)

Topics: [glsl](<https://devfeed.tech/topics/glsl.md>), [real-time](<https://devfeed.tech/topics/real-time.md>), [App](<https://devfeed.tech/topics/app.md>), [Web](<https://devfeed.tech/topics/web.md>), [API](<https://devfeed.tech/topics/api.md>), [Template](<https://devfeed.tech/topics/template.md>)

Tags: [3d](<https://devfeed.tech/tags/3d.md>), [api](<https://devfeed.tech/tags/api.md>), [app](<https://devfeed.tech/tags/app.md>), [audio](<https://devfeed.tech/tags/audio.md>), [generation](<https://devfeed.tech/tags/generation.md>), [glsl](<https://devfeed.tech/tags/glsl.md>), [hackathon](<https://devfeed.tech/tags/hackathon.md>), [interactive-3d](<https://devfeed.tech/tags/interactive-3d.md>), [real-time](<https://devfeed.tech/tags/real-time.md>), [shopify](<https://devfeed.tech/tags/shopify.md>), [web](<https://devfeed.tech/tags/web.md>)

### AI overview

Shopify's Hack Days team built a prototype for music-playing product pages in three days. The project combined a Shopify app, audio playback, per-track purchasing, GLSL visualizers driven by real-time audio, synced lyrics, and tour-date information.

### Source excerpt

How a Hack Days team built a music player, custom GLSL visualizers, and an artist toolkit for storefronts, all in three days.

## Clustering billions of products for agentic commerce with Catalog API

DevFeed: [Clustering billions of products for agentic commerce with Catalog API](<https://devfeed.tech/articles/clustering-billions-of-products-for-agentic-commerce-with-catalog-api-1341.md>)

Original publisher: [Read original article](<https://shopify.engineering/catalog-clustering>)

Author: Mariya Mansurova

Published: 2026-06-17T16:54:51Z

Content type: article

Language: en

Sources: [Shopify Engineering](<https://devfeed.tech/sources/shopify-engineering.md>), [Shopify Engineering - Shopify Engineering](<https://devfeed.tech/sources/shopify-engineering-shopify-engineering.md>)

Topics: [AI search](<https://devfeed.tech/topics/ai-search.md>), [AI Bots](<https://devfeed.tech/topics/ai-bots.md>), [SDK](<https://devfeed.tech/topics/sdk.md>)

Tags: [agentic](<https://devfeed.tech/tags/agentic.md>), [agents](<https://devfeed.tech/tags/agents.md>), [ai](<https://devfeed.tech/tags/ai.md>), [api](<https://devfeed.tech/tags/api.md>), [data](<https://devfeed.tech/tags/data.md>), [developers](<https://devfeed.tech/tags/developers.md>), [llm](<https://devfeed.tech/tags/llm.md>), [products](<https://devfeed.tech/tags/products.md>), [search](<https://devfeed.tech/tags/search.md>), [shopify](<https://devfeed.tech/tags/shopify.md>)

### AI overview

Shopify describes an LLM-powered product-clustering pipeline that reconciles differently structured merchant listings into universal product groups for AI-agent search through the Catalog API.

### Source excerpt

Building an LLM-powered pipeline to match product listings across millions of merchants into a unified catalog that AI agents can search.

## Teaching Sidekick to say no: automated data curation with LLM judge consensus

DevFeed: [Teaching Sidekick to say no: automated data curation with LLM judge consensus](<https://devfeed.tech/articles/teaching-sidekick-to-say-no-automated-data-curation-with-llm-judge-consensus-1616.md>)

Original publisher: [Read original article](<https://shopify.engineering/sidekick-curation>)

Author: Shuang Xie

Published: 2026-06-15T19:30:00Z

Content type: article

Language: en

Sources: [Shopify Engineering](<https://devfeed.tech/sources/shopify-engineering.md>), [Shopify Engineering - Shopify Engineering](<https://devfeed.tech/sources/shopify-engineering-shopify-engineering.md>)

Topics: [data](<https://devfeed.tech/topics/data.md>), [Large Language Model](<https://devfeed.tech/topics/llm.md>), [Fine-tuning](<https://devfeed.tech/topics/fine-tuning.md>), [AI Development](<https://devfeed.tech/topics/ai-development.md>), [AI Foundation Models](<https://devfeed.tech/topics/ai-foundation-models.md>), [Training AI Models](<https://devfeed.tech/topics/training-ai-models.md>), [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>), [Open Source Models & Datasets](<https://devfeed.tech/topics/open-source-models-datasets.md>), [Open Source](<https://devfeed.tech/topics/open-source.md>)

Tags: [agentic](<https://devfeed.tech/tags/agentic.md>), [ai](<https://devfeed.tech/tags/ai.md>), [analysis](<https://devfeed.tech/tags/analysis.md>), [customer](<https://devfeed.tech/tags/customer.md>), [data](<https://devfeed.tech/tags/data.md>), [feature-engineering](<https://devfeed.tech/tags/feature-engineering.md>), [fine-tuning](<https://devfeed.tech/tags/fine-tuning.md>), [llm](<https://devfeed.tech/tags/llm.md>), [open-source](<https://devfeed.tech/tags/open-source.md>), [shopify](<https://devfeed.tech/tags/shopify.md>), [training](<https://devfeed.tech/tags/training.md>)

### AI overview

Shopify Engineering describes how Sidekick's production training data failed to teach refusal behavior because it contained only successful merchant queries. The article presents automated data curation using consensus among LLM judges to identify blind spots and improve an AI assistant built from an outer planner and specialized skill models.

### Source excerpt

Production training data only captures successful queries; it can't teach a model when to say no. We built an automated curation pipeline using LLM judge consensus to close that gap.

## Quick: An internal hosting platform for the AI era

DevFeed: [Quick: An internal hosting platform for the AI era](<https://devfeed.tech/articles/quick-an-internal-hosting-platform-for-the-ai-era-1525.md>)

Original publisher: [Read original article](<https://shopify.engineering/quick>)

Author: Daniel Beauchamp

Published: 2026-06-10T12:49:23Z

Content type: article

Language: en

Sources: [Shopify Engineering](<https://devfeed.tech/sources/shopify-engineering.md>), [Shopify Engineering - Shopify Engineering](<https://devfeed.tech/sources/shopify-engineering-shopify-engineering.md>)

Topics: [hosting](<https://devfeed.tech/topics/hosting.md>), [Shopify](<https://devfeed.tech/topics/shopify.md>), [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>), [API](<https://devfeed.tech/topics/api.md>), [Cloud](<https://devfeed.tech/topics/cloud.md>), [nginx](<https://devfeed.tech/topics/nginx.md>), [HTML](<https://devfeed.tech/topics/html.md>), [Filesystems](<https://devfeed.tech/topics/filesystems.md>), [Web Development](<https://devfeed.tech/topics/web-development.md>)

Tags: [ai](<https://devfeed.tech/tags/ai.md>), [api](<https://devfeed.tech/tags/api.md>), [cloud](<https://devfeed.tech/tags/cloud.md>), [hosting](<https://devfeed.tech/tags/hosting.md>), [html](<https://devfeed.tech/tags/html.md>), [server](<https://devfeed.tech/tags/server.md>), [shopify](<https://devfeed.tech/tags/shopify.md>), [storage](<https://devfeed.tech/tags/storage.md>)

### AI overview

Shopify's Quick is an internal hosting platform that lets employees publish folders of HTML and assets to secure, employee-only URLs without frameworks, deployment pipelines, or configuration files. The article describes its Google Cloud Storage and NGINX architecture, Identity-Aware Proxy authentication, local-folder upload workflow, and planned API capabilities for data, file storage, and AI-related functionality.

### Source excerpt

Quick lets anyone at Shopify ship a site in seconds. It has changed the culture of how we build and share.

## How Shopify Built the Infrastructure Beneath Its Slack-Native River AI Agent

DevFeed: [How Shopify Built the Infrastructure Beneath Its Slack-Native River AI Agent](<https://devfeed.tech/articles/under-the-river-1654.md>)

Original publisher: [Read original article](<https://shopify.engineering/under-the-river>)

Author: Burke Libbey

Published: 2026-05-28T12:30:02Z

Content type: opinion

Language: en

Sources: [Shopify Engineering](<https://devfeed.tech/sources/shopify-engineering.md>), [Shopify Engineering - Shopify Engineering](<https://devfeed.tech/sources/shopify-engineering-shopify-engineering.md>)

Topics: [AI Agent](<https://devfeed.tech/topics/ai-agent.md>), [Slack](<https://devfeed.tech/topics/slack.md>), [monorepo](<https://devfeed.tech/topics/monorepo.md>), [Nix](<https://devfeed.tech/topics/nix.md>), [software-development](<https://devfeed.tech/topics/software-development.md>), [Pull Request](<https://devfeed.tech/topics/pull-request.md>)

Tags: [agent](<https://devfeed.tech/tags/agent.md>), [ai-agent](<https://devfeed.tech/tags/ai-agent.md>), [ai-coding](<https://devfeed.tech/tags/ai-coding.md>), [cache](<https://devfeed.tech/tags/cache.md>), [monorepo](<https://devfeed.tech/tags/monorepo.md>), [slack](<https://devfeed.tech/tags/slack.md>), [test](<https://devfeed.tech/tags/test.md>)

### AI overview

Shopify describes how it built River, an AI agent that operates in company Slack, and the infrastructure choices that supported it. The article covers Shopify's move to a monorepo, adoption of Nix for reproducible environments, and the resulting changes to CI, merge queues, build caching, testing, and repository navigation.

### Source excerpt

What it took to ship our Slack-native agent River, lessons learned, and the substrate that runs beneath it. Co-authored by River.

## We replaced Redis with MySQL for inventory reservations--and it scaled

DevFeed: [We replaced Redis with MySQL for inventory reservations--and it scaled](<https://devfeed.tech/articles/we-replaced-redis-with-mysql-for-inventory-reservations-and-it-scaled-1564.md>)

Original publisher: [Read original article](<https://shopify.engineering/scaling-inventory-reservations>)

Author: Emilie Noel

Published: 2026-05-12T16:51:53Z

Content type: article

Language: en

Sources: [Shopify Engineering](<https://devfeed.tech/sources/shopify-engineering.md>), [Shopify Engineering - Shopify Engineering](<https://devfeed.tech/sources/shopify-engineering-shopify-engineering.md>)

Topics: [MySQL](<https://devfeed.tech/topics/mysql.md>), [Redis](<https://devfeed.tech/topics/redis.md>), [Database](<https://devfeed.tech/topics/database.md>), [Shopify](<https://devfeed.tech/topics/shopify.md>), [Transactions](<https://devfeed.tech/topics/transactions.md>)

Tags: [database](<https://devfeed.tech/tags/database.md>), [ecommerce](<https://devfeed.tech/tags/ecommerce.md>), [mysql](<https://devfeed.tech/tags/mysql.md>), [payment-processing](<https://devfeed.tech/tags/payment-processing.md>), [performance](<https://devfeed.tech/tags/performance.md>), [redis](<https://devfeed.tech/tags/redis.md>), [scale](<https://devfeed.tech/tags/scale.md>), [shopify](<https://devfeed.tech/tags/shopify.md>), [transactions](<https://devfeed.tech/tags/transactions.md>)

### AI overview

Shopify explains how it replaced Redis with MySQL for inventory reservations during checkout. Using one row per inventory unit, SKIP LOCKED, composite primary keys, and connection visibility, the rebuilt system met high-throughput and consistency requirements during peak Black Friday 2025 traffic.

### Source excerpt

How we used SKIP LOCKED, composite primary keys, and connection visibility to hit our scale targets.

## Flow generation through natural language: An agentic modeling approach

DevFeed: [Flow generation through natural language: An agentic modeling approach](<https://devfeed.tech/articles/flow-generation-through-natural-language-an-agentic-modeling-approach-1390.md>)

Original publisher: [Read original article](<https://shopify.engineering/fine-tuning-agent-shopify-flow>)

Author: Ted Chaiwachirasak

Published: 2026-04-22T12:32:02Z

Content type: article

Language: en

Sources: [Shopify Engineering](<https://devfeed.tech/sources/shopify-engineering.md>), [Shopify Engineering - Shopify Engineering](<https://devfeed.tech/sources/shopify-engineering-shopify-engineering.md>)

Topics: [AI Bots](<https://devfeed.tech/topics/ai-bots.md>), [AI Chat](<https://devfeed.tech/topics/ai-chat.md>)

Tags: [agent](<https://devfeed.tech/tags/agent.md>), [agentic](<https://devfeed.tech/tags/agentic.md>), [ai](<https://devfeed.tech/tags/ai.md>), [automation](<https://devfeed.tech/tags/automation.md>), [benchmark](<https://devfeed.tech/tags/benchmark.md>), [fine-tuning](<https://devfeed.tech/tags/fine-tuning.md>), [model](<https://devfeed.tech/tags/model.md>), [synthetic](<https://devfeed.tech/tags/synthetic.md>), [training](<https://devfeed.tech/tags/training.md>), [workflow](<https://devfeed.tech/tags/workflow.md>)

### AI overview

Shopify describes fine-tuning Qwen3-32B into a tool-calling agent that generates Flow automations from natural-language requests. The article focuses on constructing synthetic training data from validated workflows and evaluating the resulting model.

### Source excerpt

We fine-tuned Qwen3-32B into a tool-calling agent that generates Flow automations from natural language--faster, cheaper, and more accurate than the frontier model it replaced, with a weekly retraining flywheel built on real merchant data.

[Next page](<https://devfeed.tech/sources/shopify-engineering.md?cursor=WyIyMDI2LTA0LTIyVDEyOjMyOjAyKzAwOjAwIiwgImIyZjlmNDBkLTNlZTEtNGQ2ZC05NWFhLTJiZTllNGFmOWQ4MSJd>)