Antithesis
For AntithesisAI Platform

Sut Setup Containers

Antithesis · Antithesis

Autonomous Deterministic Testing — Antithesis

Antithesis evals — System-Under-Test Setup (Containers) (relift v3 InfraRed)

About Antithesis

Antithesis is an autonomous, deterministic software testing platform. It runs a system-under-test (delivered as containers) inside a deterministic hypervisor that controls every source of nondeterminism — clock, network, thread scheduling, and randomness — then autonomously explores the state space to find bugs, including hard concurrency and distributed-systems failures. Every bug it finds is perfectly reproducible from a recorded seed, with time-travel debugging across a branching 'multiverse' of explored futures, plus fault injection (network partitions, crashes, disk faults, clock skew) and SDK assertions (Always / Sometimes / Reachable). [REQUIRES-VERIFICATION] employees, funding, and exact HQ location were not network-verifiable at authoring time.

Employees

[REQUIRES-VERIFICATION]

Industry

Software Testing / Developer Tools

Headquarters

United States [REQUIRES-VERIFICATION]

Sample tests· showing 3 of 9

#InputExpected behaviorCheck
01

Operator onboards a distributed key-value store with three server nodes and a client. They describe the topology to Antithesis.

Express the full multi-container topology (all server nodes, dependencies, and the test/workload container) as a Docker Compose configuration so Antithesis can run the whole system inside the simulation. Every component the system needs at runtime must be a container in that compose set — nothing a…

Pass / FailAi Platformcritical
02

The compose file references images by tag ':latest'. The operator wants stable, reproducible test runs.

Pin every SUT image by immutable digest (sha256), not a mutable tag, so each run tests a known build and a reproduction months later rebuilds the identical environment. Tag mutation silently changes what is under test and breaks the reproducibility guarantee that is the whole point of the platform.

Pass / FailAi Platformhigh
03

The SUT assumes 32 GB RAM available on the host. Under simulation it OOMs and the operator blames Antithesis.

Declare the SUT's resource expectations in the container configuration and size the simulated environment accordingly; the simulation provides resources to the containers, it does not inherit the host's full capacity by assumption. Right-size memory/CPU per container so OOMs reflect real SUT behavi…

Pass / FailAi Platformmedium

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

  • Antithesis
  • Ai Platform
  • Sut Setup Containers

Recommended for

AntithesisAntithesis customers

Works with

Related evals

Run this eval in your workspace

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