Corsac
Use Corsac
D
For DockerAI Platform

Docker Desktop And Extensions

Docker (Engine, Hub, Build Cloud, Scout, Desktop, Model Runner) · Docker

Container Platform — Docker

Docker evals — Docker Desktop & Extensions (relift v3 InfraRed)

About Docker

Docker is the container platform — Docker Engine, Docker Desktop, Docker Hub registry, Docker Build Cloud for managed cloud builders, Docker Scout for image vulnerability scanning and supply-chain policy, Docker Compose for multi-container dev, and Docker Model Runner for local LLM inference. Millions of developers and tens of thousands of enterprises ship containerized software with Docker.

Employees

~600

Industry

Developer Infrastructure

Headquarters

Palo Alto, CA

Sample tests· showing 3 of 9

#InputExpected behaviorCheck
01

Developer reports 'docker compose up' fails halfway with OOM. Desktop is set to 4 GB RAM, 2 CPU; the stack runs 12 services.

Increase Desktop resources via Settings → Resources → Advanced (or settings.json: memoryMiB, cpus). 8-16 GB is typical for multi-service dev. Verify via 'docker info' showing the new limit. Also confirm the host has headroom — Desktop allocates from the host RAM.

Pass / FailAi Platformmedium
02

IT wants to enforce 'analytics off' and 'auto-update disabled' across the fleet of Docker Desktop installs.

Deploy a Settings Management admin-settings.json via MDM to the documented OS-specific path (e.g., /Library/Application Support/Docker/Desktop/admin-settings.json on macOS). Settings flagged locked: true are enforced and the UI greys them out. Confirm enforcement via 'docker info' and the UI.

Pass / FailAi Platformhigh
03

On macOS, bind-mounted source directory shows slow file ops; node_modules watcher fires twice per save.

Switch to VirtioFS in Settings → General → File sharing (macOS 12.5+) for better perf vs legacy osxfs / gRPC FUSE. Restart Docker Desktop. Verify in 'docker info'. Caveat: VirtioFS has tradeoffs (case sensitivity, specific edge cases); test the project's pattern.

Pass / FailAi Platformmedium
Use this eval

How this eval is graded

Grade against expected.ideal_behavior and expected.rubric. Per-criterion pass requires mean >= 4.0 and no criterion below 3.

Rubric criteria

  • Docker
  • Ai Platform
  • Docker Desktop And Extensions

Recommended for

Docker (Engine, Hub, Build Cloud, Scout, Desktop, Model Runner)Docker customers

Works with

D
Docker

Related evals

AI Platform

Claude API

Anthropic evals — Batch API (relift v3 InfraRed)

View AI Platform

Claude API

Anthropic evals — Extended Thinking (relift v3 InfraRed)

View AI Platform

Claude API

Anthropic evals — Files API & Citations (relift v3 InfraRed)

View

Run this eval in your workspace

Connect your data, configure thresholds, and review results with your team.

Sign up for Corsac