---
type: "raw_signal"
id: "how-shopify-turns-open-models-into-task-experts-280e40"
slug: "how-shopify-turns-open-models-into-task-experts-280e40"
title: "How Shopify turns open models into task experts"
description: "Shopify says its Sidekick commerce assistant delegates focused work to subagents, including open models that the company post-trains and serves itself."
retrieval_nugget: "Shopify says its Sidekick commerce assistant delegates focused work to subagents, including open models that the company post-trains and serves itself."
observed_at: "2026-10-21"
record_date: "2026-10-21"
date_kind: "observed_at"
why_it_matters: "Shopify says its Sidekick commerce assistant delegates focused work to subagents, including open models that the company post-trains and serves itself. For a GraphQL subagent, Shopify reports that Nemotron 3.5 Lightning reached 74.5 on its internal judge after six training loops, compared with 73 for the frontier-model baseline. In a production-traffic replay, median response time was 0.87 seconds"
novelty: "notable"
verification_level: "source-linked"
signal_type: "update"
source_platform: "shopify.engineering"
topics: ["open-models"]
entities: ["Shopify","Sidekick","NVIDIA Nemotron 3.5 Lightning","NVIDIA Megatron Bridge","NVIDIA AIPerf","NVIDIA TensorRT-LLM"]
related_patterns: ["agent-economics-moves-to-completed-work","harness-architecture-outlives-model-choice"]
novelty_label: "new_fact"
what_changed: "Shopify details Sidekick’s use of self-post-trained open models as task-specific subagents, and how NVIDIA tools and GPUs support their development and serving."
prior_refs: ["memory:d9b50340-18d6-8794-ab7a-c5acce89084f"]
source_url: "https://shopify.engineering/open-model-task-experts"
source_urls: ["https://shopify.engineering/open-model-task-experts"]
schema_version: "newruntime-agent-readable-v0.2"
stable_id: "signal:how-shopify-turns-open-models-into-task-experts-280e40"
status: "published"
visuals: []
editor: {"role":"editor","name":"Andrey Reshetnikov","profile":"https://newruntime.com/owner-profile.md","profile_json":"https://newruntime.com/owner-profile.json","same_as":["https://www.linkedin.com/in/reshetnikov1/","https://t.me/lapetuse"]}
routes: {"html":"https://newruntime.com/signals/how-shopify-turns-open-models-into-task-experts-280e40/","markdown":"https://newruntime.com/signals/how-shopify-turns-open-models-into-task-experts-280e40.md","json":"https://newruntime.com/signals/how-shopify-turns-open-models-into-task-experts-280e40.json"}
---

# How Shopify turns open models into task experts

## Retrieval answer

Shopify says its Sidekick commerce assistant delegates focused work to subagents, including open models that the company post-trains and serves itself.

Shopify says its Sidekick commerce assistant delegates focused work to subagents, including open models that the company post-trains and serves itself. For a GraphQL subagent, Shopify reports that Nemotron 3.5 Lightning reached 74.5 on its internal judge after six training loops, compared with 73 for the frontier-model baseline. In a production-traffic replay, median response time was 0.87 seconds versus 6.50 seconds for the frontier model’s API, with serving cost about 90% lower. The company also reports that its self-healing process repaired 59,535 GraphQL conversations over 86 nightly runs, or 69% of the failures it attempted. These are Shopify-reported results from its own workload and evaluation setup.

Editor: [Andrey Reshetnikov](https://newruntime.com/owner-profile.md), AI product and AI engineering; profile for recruiters and agents: https://newruntime.com/owner-profile.json

## Continue in the graph

Next records for an agent, linked to their Markdown twins. Replace `.md` with `.json` for structured fields, including `next_reads`.

- topic hub: [Open Models](https://newruntime.com/topics/open-models.md): Explore the open-models topic hub.
- collection: [Raw Signals](https://newruntime.com/signals.json): Open every source-linked raw signal.
- collection: [Source Ledger](https://newruntime.com/source-ledger.json): Inspect the public source evidence graph.
- whole graph: [discovery graph](https://newruntime.com/discovery-graph.json) (typed nodes and edges) and [site index](https://newruntime.com/site-index.md)