Skip to Main Content
Trunchbull

Sandboxing / controlled machines for agent evaluation

Give agents room to work. Keep the boundary.

Run terminal and code-execution workloads inside isolated, image-backed environments—with a complete tool surface and evidence for every execution.

Explore the platform
SANDBOX SESSION / LEASE 7F2AISOLATED

terminal-agent / ubuntu:24.04

IMMUTABLE IMAGE · STANDARD-4

02:14 ACTIVE

filesystem

/app mounted and ready

SCOPED

command_execute

python /app/evaluate.py

EXIT 0

network

environment policy applied

CONTROLLED

lease

released when evaluation completes

ACTIVE

08

COMMANDS

03

ARTIFACTS

00

VIOLATIONS

4 CAPABILITIES GRANTEDBOUNDARY ACTIVE

RUNTIME

Isolated

container-backed execution boundary

TOOL SURFACE

Files + shell

commands, processes, and terminals

PUBLIC DEMO

Coming soon

guided sandbox and technical write-up

01 / Real environment isolation

Give every workload its own controlled runtime.

Run terminal and code-execution evaluations inside isolated container environments instead of handing an agent access to your machine. Each environment has an explicit image, compute profile, network policy, and scoped lease.

  • Public container images resolved into reproducible deployments
  • Explicit compute, storage, network, and lifecycle policy
  • Environment access scoped to an authorized execution lease
ENVIRONMENT POLICYTERMINAL-BENCH / REGEX-LOG

Runtime image

resolved to immutable source digest

PINNED

Compute profile

explicit CPU, memory, and storage

LIMITED

Network policy

declared for this environment

APPLIED

Execution lease

scoped capability and expiration

SCOPED
POLICY APPLIED BEFORE LEASE

02 / A complete execution surface

Let agents work through tools you can observe.

Expose the machine as a structured capability surface. Models can inspect files, execute commands, manage processes, and use an interactive terminal while Trunchbull records the operations required to evaluate the result.

  • File read, write, list, move, and delete operations
  • Command execution and managed background processes
  • Interactive terminal sessions with controlled input and output
SANDBOX CAPABILITIES5 OF 5 AVAILABLE

file_read

Inspect workspace content

READY

file_write

Create evaluation artifacts

READY

command_execute

Run bounded shell commands

RUNNING

process_list

Inspect managed processes

READY

terminal_open

Start an interactive session

READY

03 / Public demo space

Try the sandbox yourself soon.

We are preparing a public space where you can inspect the environment, run a constrained task, and see the same execution evidence Trunchbull captures during a benchmark.

  • No local installation required
  • Guided terminal and filesystem task
  • Technical architecture write-up to follow
PUBLIC SANDBOXPREVIEW

GUIDED ENVIRONMENT / 01

Open a terminal. Complete a task. Inspect the boundary.

A public, constrained sandbox with the execution trace visible beside it.

DEMO SPACE IN PREPARATION
NO INSTALL REQUIREDCOMING SOON

From image to evidence

A controlled environment in three moves.

Choose the runtime, grant the execution a scoped lease, and inspect the recorded work before the environment is released.

  1. 01

    Define the environment

    Select an image and explicit compute, storage, and network policy.

  2. 02

    Lease scoped access

    Give the evaluation only the sandbox capabilities it requires.

  3. 03

    Execute and verify

    Record operations, inspect artifacts, grade the result, and release the lease.

SANDBOX LIFECYCLEONE EVALUATION
01Provision environmentIMAGE READY
02Issue scoped leaseBOUNDARY ACTIVE
03Execute agent taskOPERATIONS RECORDED
04Verify and releaseEVIDENCE SAVED

Public demo coming soon

See the boundary, not just the benchmark.

The public sandbox and a detailed architecture write-up are next. Until then, create a workspace to run controlled environments with your own evaluations.