---
schema: "swft.publication/v1"
id: "company-shopify-river-aquifer"
title: "Shopify River and Aquifer: one durable platform for many software agents"
description: "How Shopify combines River, Aquifer, its World monorepo, Nix environments, Roast workflows, sandboxes, proof loops, and human review."
summary: "Shopify reported that it was rolling Aquifer out profile by profile as one shared foundation for several kinds of agents. River works with employees in Slack. Aquifer is designed to preserve the session and supply temporary sandboxes, tools, credentials, and activity records. Roast adds repeatable checked workflows, and Dispatch shows how a specialist factory can require proof before review."
canonical: "https://swft.io/companies/shopify-river-aquifer"
author: "SWFT Editorial"
author_type: "Organization"
published: "2026-09-01"
modified: "2026-09-02"
kind: "case-study"
section: "Companies"
tags: ["Shopify River", "Shopify Aquifer", "Shopify Roast", "agent platform", "durable agent sessions", "AI software factory"]
evidence_labels: ["INFERENCE", "OBS", "SELF-REPORT"]
source_ids: ["shopify-dispatch", "shopify-roast", "shopify-under-the-river"]
authorship_disclosure: "AI-drafted from the cited public sources and independently checked by a second AI editorial-review agent (Codex) for source fit, claim boundaries, overlap, and reader utility. SWFT Editorial is responsible for corrections."
---

# Shopify River and Aquifer: one durable platform for many software agents

Shopify runs River in public Slack threads while rolling Aquifer out profile by profile as a shared foundation for sessions, sandboxes, controls, and agent profiles.

> **Authorship:** AI-drafted from the cited public sources and independently checked by a second AI editorial-review agent (Codex) for source fit, claim boundaries, overlap, and reader utility. SWFT Editorial is responsible for corrections.

## Quick answer

Shopify reported that it was rolling Aquifer out profile by profile as one shared foundation for several kinds of agents. River works with employees in Slack. Aquifer is designed to preserve the session and supply temporary sandboxes, tools, credentials, and activity records. Roast adds repeatable checked workflows, and Dispatch shows how a specialist factory can require proof before review.

Shopify built a shared foundation for many kinds of software agents. River is the visible agent in Slack. When Shopify described the architecture in May 2026, Aquifer was still rolling out underneath River, profile by profile. It is designed to keep sessions, tools, sandboxes, credentials, and activity records on one shared foundation. Roast turns repeatable work into checked workflows. The reusable idea is the platform around the model.

## What are Shopify River and Aquifer?

[Shopify describes River](https://shopify.engineering/under-the-river) as an internal coding agent that works in public company Slack channels. An employee mentions River, and it can read code, run tests, query the data warehouse, inspect production traces, and open a pull request. Other employees can join the thread with a constraint or correction while the work is still running.

Shopify reported in May 2026 that River coauthored one in eight merged pull requests. That is a company self-report about participation. It does not mean River independently designed, approved, or merged one eighth of Shopify's software.

Aquifer is the internal platform Shopify was rolling out beneath River. Shopify separates three parts:

- The **session** is the durable record of the work. It keeps an append-only history even when a process stops.
- The **harness** is the agent loop that reads the history, chooses a next action, and calls the model.
- The **sandbox** is the temporary workspace where code, commands, builds, and tests run.

This separation lets a session survive a failed or replaced sandbox. It also keeps model decisions observable outside the place where code executes.

## Why did Shopify prepare the codebase first?

Shopify moved its software into a monorepo called World and standardized development, continuous integration, and production environments with Nix. The company says those decisions gave agents one navigable codebase and a reproducible environment.

That foundation matters to a product team because an agent needs more than source code. It needs to know which commands are valid, which systems depend on a change, how to reproduce a failure, and whether a result passed the same checks people use. Shopify stores written operating knowledge as skills that can be loaded when relevant.

As that rollout progresses, Aquifer is designed to support several modes on the same foundation. River is an interactive profile with a person present. Pull-request review is an automated profile woken by an outside event. Batch and continuous-integration work can run as temporary jobs. Shopify describes each profile as configuration for its prompt, skills, extensions, sandbox policy, and model defaults rather than a new platform.

## What is Shopify Roast?

[Roast](https://shopify.engineering/introducing-roast) is Shopify's open-source framework for structured AI workflows. A workflow can alternate ordinary commands with model or coding-agent steps, share context between steps, run work in parallel, branch, retry, and save a session for replay.

Shopify's Boba workflow shows why this hybrid design is useful. Deterministic commands clean a Ruby file and run Sorbet's automatic fixes. A coding agent then handles the remaining type errors, reruns tests, and continues until the declared checks pass. Ordinary software owns the predictable operations. The agent handles the part that requires interpretation.

Shopify says internal Roast workflows have analyzed thousands of test files and improved tests and type coverage. The public article does not provide a controlled comparison, a failure rate, or a defect series for those uses.

## How does Shopify prove security findings before asking for review?

Shopify's application-security team built a separate factory line called Dispatch. Its [July 2026 account](https://shopify.engineering/building-an-agentic-harness-that-outlasts-the-model) describes parallel hunter agents that search bounded code partitions, a verifier that must demonstrate a finding with a real test, and remediation agents that prepare a branch and draft pull request.

Candidate findings are not treated as confirmed simply because a model sounds confident. The verifier must use the application's existing integration or functional test tools to demonstrate real impact. Findings that cannot meet the proof rule are rejected or downgraded. Deterministic software, rather than an agent, controls credentials, Git operations, and stored results.

Shopify reported complete scans of more than 80 applications, thousands of scans in roughly six weeks, and more than 300 findings. It valued those findings at more than $400,000 in equivalent bug-bounty payouts. These figures are Shopify's own operating estimates, not an independent security audit or a measurement of River as a whole.

## What can a product team copy?

Build one dependable agent platform before creating many named agents. Keep the work record outside the disposable execution environment. Give every profile the same identity, credential, observability, and sandbox boundaries. Put predictable steps in ordinary code and reserve agent judgment for the uncertain middle. Require a complete evidence package before a result reaches a human approval gate.

Shopify's strongest evidence is architectural and operational. River, Aquifer, and Dispatch remain internal, while Roast is open source. Public material does not disclose company-wide acceptance rates, defects, review time, or the customer impact of agent-assisted changes.

## How we know

- **First-party report (SELF-REPORT)** Shopify describes River's Slack workflow, one-in-eight coauthorship figure, World and Nix foundation, and Aquifer's profile-by-profile rollout plus its durable session, harness, sandbox, gateway, and profile architecture. Sources: [Under the River](https://shopify.engineering/under-the-river).
- **Observed artifact (OBS)** Shopify presents Roast as an open-source framework for versioned workflows that combine deterministic execution with model and coding-agent steps. Sources: [Introducing Roast: Structured AI workflows made easy](https://shopify.engineering/introducing-roast).
- **First-party report (SELF-REPORT)** Shopify describes Dispatch's partitioned searches, test-oracle verification, remediation pull requests, application coverage, finding count, and estimated bug-bounty value. Sources: [Building an agentic harness that outlasts the model](https://shopify.engineering/building-an-agentic-harness-that-outlasts-the-model).
- **Analysis (INFERENCE)** SWFT treats Shopify's durable shared substrate and deterministic proof boundaries as more reusable than any single model or named agent. Sources: [Under the River](https://shopify.engineering/under-the-river); [Introducing Roast: Structured AI workflows made easy](https://shopify.engineering/introducing-roast); [Building an agentic harness that outlasts the model](https://shopify.engineering/building-an-agentic-harness-that-outlasts-the-model).

## Sources

- **First-party report (SELF-REPORT)** [Building an agentic harness that outlasts the model](https://shopify.engineering/building-an-agentic-harness-that-outlasts-the-model) — Shopify Engineering; published 2026-07-29; accessed 2026-09-01. Shopify's account of Dispatch, a multi-agent security line with partitioning, shared context, hunter and verifier roles, real tests, severity handling, and draft remediation pull requests.
- **First-party report (SELF-REPORT)** [Introducing Roast: Structured AI workflows made easy](https://shopify.engineering/introducing-roast) — Shopify Engineering; published 2025-06-18; accessed 2026-09-01. Shopify's account of extracting an internal structured-workflow tool into an open-source project for versioned deterministic and agent steps.
- **First-party report (SELF-REPORT)** [Under the River](https://shopify.engineering/under-the-river) — Shopify Engineering; published 2026-05-28; accessed 2026-09-01. Shopify's account of the World monorepo, reproducible environments, public-to-the-company River sessions, durable Aquifer substrate, profiles, internal scale, and rollout limits.

## Read next

- [Cloudflare's AI engineering stack: a control plane for company-wide agents](/companies/cloudflare-ai-engineering-stack)
- [Spotify Honk: adding an agent to a software factory that already worked](/companies/spotify-honk)
- [How an AI software factory works](/software-factory-architecture)