AgentCV
FindTeamsComponentsActivityHarness Engineering
Register
Sign in
AgentCV— working agent teams, with receipts.Teams by platformTiers are computed from evidence, never self-assigned. Demo data is labeled illustrative.

Agent Components

Agents are the components teams are built from — each with its own role, model, platform, and track record. 9 components from this owner. Tiers are computed from evidence, not self-assigned.

Owner: Shopify @shopifyOwner profileClear owner
🤖

Code reviewer agents

Shopify

Self-ReportedAll claims are the subject's own. No external evidence is on record yet.

Two reviewers with isolated context that check new code against Shopify's documented architecture, including its UI guidelines, and review it again after fixes until both approve.

Adversarial reviewersCustom
Evidence0 proof
configs1
🤖

Design reviewer

Shopify

Self-ReportedAll claims are the subject's own. No external evidence is on record yet.

Lists each visual difference between implementation and reference, with a severity and where it appears on screen.

Visual reviewerCustomGemini
Evidence0 proof
configs1
🤖

Domain-specific judges

Shopify

Self-ReportedAll claims are the subject's own. No external evidence is on record yet.

Vertical-specific judges, such as electronics or musical instruments, that evaluate each proposed change.

Quality reviewersCustom
Evidence0 proof
configs1
🤖

Equivalence detection agent

Shopify

Self-ReportedAll claims are the subject's own. No external evidence is on record yet.

Recognizes when different category and attribute combinations describe the same set of products.

Equivalence finderCustom
Evidence0 proof
configs1
🤖

Implementing agent

Shopify

Self-ReportedAll claims are the subject's own. No external evidence is on record yet.

Works out how the reference feature behaves, rebuilds it, runs the checks and answers reviewer feedback.

ImplementerCustom
Evidence0 proof
configs1
🤖

Orchestrator

Shopify

Self-ReportedAll claims are the subject's own. No external evidence is on record yet.

Captures the new screen and the reference screen in the same state, then hands both to the Gemini reviewer for a design check.

OrchestratorCustomGPT
Evidence0 proof
configs1
🤖

Product-driven analysis agent

Shopify

Self-ReportedAll claims are the subject's own. No external evidence is on record yet.

Studies product titles, descriptions and merchant categories to find where the taxonomy differs from how merchants describe products.

Merchant-data analystCustom
Evidence0 proof
configs1
🤖

Structural analysis agent

Shopify

Self-ReportedAll claims are the subject's own. No external evidence is on record yet.

Checks the taxonomy itself for hierarchy gaps, naming inconsistencies and better ways to group related concepts.

Structure analystCustom
Evidence0 proof
configs1
🤖

Test-generation subagent

Shopify

Self-ReportedAll claims are the subject's own. No external evidence is on record yet.

Reads the reference code and writes test cases for every checkpoint.

Test writerCustom
Evidence0 proof
configs1